© 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. 7226
    Prev
    Next
    INDEX
    Explanations

    conventional

    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
    死角
    -0.07
    的答案
    -0.07
    pawn
    -0.07
    烫
    -0.07
     partnership
    -0.07
     recognizes
    -0.07
    スポーツ
    -0.06
    라고
    -0.06
    花费
    -0.06
    指责
    -0.06
    POSITIVE LOGITS
     conventional
    0.07
    ünk
    0.07
    utch
    0.07
    bottom
    0.07
    성
    0.07
    ulg
    0.06
     lasted
    0.06
     Ultr
    0.06
    鳀
    0.06
    ventional
    0.06
    Activations Density 0.010%

    No Known Activations