© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65792
    Prev
    Next
    INDEX
    Explanations

    useful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    对其进行
    -0.08
     Affero
    -0.07
    锶
    -0.07
     didSelectRowAtIndexPath
    -0.07
    .stdin
    -0.07
    ?></
    -0.07
    UserDefaults
    -0.07
    千克
    -0.07
    派出
    -0.06
     İzmir
    -0.06
    POSITIVE LOGITS
     fx
    0.07
     cx
    0.07
    斓
    0.07
    скор
    0.07
    ANEL
    0.07
     plusieurs
    0.06
    宴会
    0.06
    包围
    0.06
     Hunt
    0.06
     mel
    0.06
    Activations Density 0.045%

    No Known Activations