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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6876
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act-logits · gemini-2.0-flash
    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
    הדפס
    -0.07
    α
    -0.06
     Lotto
    -0.06
    _↵
    -0.06
    힝
    -0.06
    OLUMN
    -0.06
     jakości
    -0.06
    行政
    -0.06
    ','
    -0.06
    _INPUT
    -0.06
    POSITIVE LOGITS
     IDEA
    0.07
    有两种
    0.07
     severed
    0.07
     BST
    0.07
    	U
    0.07
     perce
    0.07
    cb
    0.07
    .pr
    0.07
     step
    0.07
     cmd
    0.07
    Activations Density 0.068%

    No Known Activations