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. 71638
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
    _clk
    -0.07
    .setY
    -0.07
     Amy
    -0.07
    śnie
    -0.07
     getValue
    -0.06
    >k
    -0.06
    ▦
    -0.06
    '][]
    -0.06
     Batch
    -0.06
    release
    -0.06
    POSITIVE LOGITS
    收集
    0.07
    Cancelled
    0.07
     California
    0.07
     перемен
    0.07
     inferred
    0.07
     hosted
    0.06
    	input
    0.06
     constructed
    0.06
    聚
    0.06
     las
    0.06
    Activations Density 0.068%

    No Known Activations