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. 24662
    Prev
    Next
    INDEX
    Explanations

    code/character sequences

    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
    一个好的
    -0.07
    璮
    -0.07
     Cinema
    -0.07
    .APP
    -0.07
    little
    -0.06
     ques
    -0.06
    rgyz
    -0.06
     Pick
    -0.06
     urllib
    -0.06
     lớ
    -0.06
    POSITIVE LOGITS
     intersect
    0.08
    距離
    0.08
    节奏
    0.08
    RowAtIndexPath
    0.07
    LinkedIn
    0.07
    عقود
    0.07
    刷卡
    0.07
    losing
    0.07
    閉
    0.07
    驾
    0.07
    Activations Density 0.030%

    No Known Activations