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. 2550
    Prev
    Next
    INDEX
    Explanations

    softmax

    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
    丰田
    -0.07
    房产
    -0.07
    Along
    -0.07
    .Annotations
    -0.07
     Amazon
    -0.07
    Asia
    -0.07
    FOUND
    -0.07
    trand
    -0.07
     Blocks
    -0.06
     LOT
    -0.06
    POSITIVE LOGITS
     bri
    0.07
     mono
    0.07
    分からない
    0.07
     peel
    0.07
     fore
    0.07
     четыре
    0.07
    博主
    0.07
    /********************************************************
    0.07
    \d
    0.07
     performance
    0.06
    Activations Density 0.002%

    No Known Activations