© 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. 15-RESID-POST-AA
    11. 77114
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    刿
    -0.07
    _hours
    -0.07
     sunscreen
    -0.07
    天空
    -0.07
     THEN
    -0.07
    rade
    -0.07
    Senha
    -0.07
    当天
    -0.07
    andalone
    -0.07
     magically
    -0.07
    POSITIVE LOGITS
     operating
    0.09
    (ix
    0.08
    Operating
    0.07
     port
    0.07
    ,
    0.07
     faithful
    0.07
    fstream
    0.06
    堐
    0.06
    -mort
    0.06
    诊治
    0.06
    Activations Density 0.016%

    No Known Activations