© 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. 54679
    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
    :',
    -0.08
     services
    -0.07
     soul
    -0.07
    azi
    -0.07
    爱好
    -0.07
    �
    -0.07
    izards
    -0.07
    汗
    -0.07
    (data
    -0.07
    前景
    -0.06
    POSITIVE LOGITS
    ethoven
    0.07
     الخم
    0.07
    DataSetChanged
    0.07
    ﻖ
    0.07
    amment
    0.07
    weetalert
    0.07
     dern
    0.07
    𫗴
    0.07
    ꒳
    0.06
    extAlignment
    0.06
    Activations Density 0.211%

    No Known Activations