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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 53953
    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
     Sant
    -0.08
     Camp
    -0.07
    /st
    -0.07
    His
    -0.07
    -watch
    -0.07
     המ
    -0.06
    ��
    -0.06
     historic
    -0.06
    sales
    -0.06
     lộ
    -0.06
    POSITIVE LOGITS
    ArgumentException
    0.07
    锱
    0.07
     disagreed
    0.07
    .setItems
    0.07
    .Hour
    0.07
    قضايا
    0.07
     RATE
    0.07
     disposed
    0.06
    ې
    0.06
    :t
    0.06
    Activations Density 0.039%

    No Known Activations