© 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. 41198
    Prev
    Next
    INDEX
    Explanations

    avatar

    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
     wrest
    -0.07
     adamant
    -0.07
    גז
    -0.07
     pog
    -0.06
    瘴
    -0.06
    栊
    -0.06
    ;"><?
    -0.06
     congregation
    -0.06
    셤
    -0.06
    /perl
    -0.06
    POSITIVE LOGITS
    解决方案
    0.07
    的需求
    0.07
    模型
    0.07
    显然是
    0.07
    _checker
    0.07
    部件
    0.07
    _SOURCE
    0.07
     across
    0.07
     systems
    0.06
     implemented
    0.06
    Activations Density 0.001%

    No Known Activations