© 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. 7-RESID-POST-AA
    11. 77634
    Prev
    Next
    INDEX
    Explanations

    retention

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (inflater
    -0.07
    ']],
    -0.07
    stärke
    -0.07
    连连
    -0.07
    '];?></
    -0.07
    ✌
    -0.07
    (MigrationBuilder
    -0.07
    😈
    -0.07
    继
    -0.07
    センター
    -0.07
    POSITIVE LOGITS
     retention
    0.09
    媱
    0.07
    ﻫ
    0.07
     addictive
    0.07
     wooded
    0.07
    INK
    0.07
    חוז
    0.07
     حسين
    0.07
    Recursive
    0.06
     IRA
    0.06
    Activations Density 0.003%

    No Known Activations