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. 71489
    Prev
    Next
    INDEX
    Explanations

    Cautions, prohibitions, instructions

    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
    末端
    -0.07
     connector
    -0.07
     JObject
    -0.07
     Inflate
    -0.07
    orian
    -0.06
     acct
    -0.06
     tempered
    -0.06
    (recipe
    -0.06
    彝
    -0.06
    נפש
    -0.06
    POSITIVE LOGITS
     precautions
    0.06
    =".$_
    0.06
    新材料
    0.06
    ഏ
    0.06
    rea
    0.06
     Cert
    0.06
    _total
    0.06
     materials
    0.06
    穿上
    0.06
    骤
    0.06
    Activations Density 0.262%

    No Known Activations