© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 110383
    Prev
    Next
    INDEX
    Explanations

    then

    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
     ethnic
    -0.08
    举报电话
    -0.07
     Peoples
    -0.07
     uppercase
    -0.07
    が必要
    -0.07
    	                       
    -0.07
    热点
    -0.07
     "'"
    -0.07
     angry
    -0.07
     performers
    -0.07
    POSITIVE LOGITS
    יז
    0.07
    kept
    0.06
    锂
    0.06
    !↵↵
    0.06
    ヮ
    0.06
    巽
    0.06
    Spider
    0.06
    上海证券
    0.06
    氕
    0.06
    oh
    0.06
    Activations Density 0.053%

    No Known Activations