© 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. 23-RESID-POST-AA
    11. 1074
    Prev
    Next
    INDEX
    Explanations

    heroes

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -drop
    -0.07
    loss
    -0.07
    落实
    -0.07
     Munich
    -0.07
    �
    -0.07
    /open
    -0.07
    Ｊ
    -0.07
     Regression
    -0.07
    Didn
    -0.07
     mentioned
    -0.07
    POSITIVE LOGITS
    鹾
    0.08
    אלוה
    0.08
    //----------------------------------------------------------------------------↵
    0.07
    olang
    0.07
    Availability
    0.07
    );$
    0.07
     sağlıkl
    0.07
    𝖑
    0.07
    .ads
    0.06
    礞
    0.06
    Activations Density 0.039%

    No Known Activations