Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 48541
    Prev
    Next
    INDEX
    Explanations

    Forum advice/suggestions

    np_max-act-logits · gemini-2.0-flash

    suggestions or recommendations for what someone should do or consider.

    oai_token-act-pair · claude-4-5-haikuTriggered by @xiaoqingsun004
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    年至
    -0.07
    年后
    -0.07
     finalist
    -0.07
    辩护
    -0.07
    专业
    -0.06
     hc
    -0.06
    نتائج
    -0.06
     nominations
    -0.06
     finalists
    -0.06
    짠
    -0.06
    POSITIVE LOGITS
    Dirty
    0.07
    渭
    0.07
    禄
    0.07
     leopard
    0.07
     gradient
    0.07
    ujące
    0.07
     peso
    0.07
     Common
    0.07
    /course
    0.06
     questo
    0.06
    Activations Density 0.167%

    No Known Activations