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. 2590
    Prev
    Next
    INDEX
    Explanations

    good

    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
    FontSize
    -0.08
    .Encode
    -0.08
    ✍
    -0.07
     taco
    -0.07
    vendor
    -0.07
    shiv
    -0.07
     Expand
    -0.07
     Pavel
    -0.06
    טלוו
    -0.06
    ».
    -0.06
    POSITIVE LOGITS
    ちゃん
    0.07
    .TryGetValue
    0.07
    ()]);↵
    0.06
     gebruik
    0.06
     Disability
    0.06
     Cult
    0.06
    债
    0.06
    冲突
    0.06
    的心理
    0.06
    (pkt
    0.06
    Activations Density 0.006%

    No Known Activations