© 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. 11-RESID-POST-AA
    11. 5119
    Prev
    Next
    INDEX
    Explanations

    refs

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Demp
    -0.08
     ans
    -0.07
    esture
    -0.07
    빼
    -0.07
    媽媽
    -0.07
     כניס
    -0.07
    Put
    -0.06
    -move
    -0.06
    .Background
    -0.06
    秉
    -0.06
    POSITIVE LOGITS
    ɘ
    0.07
    лы
    0.07
    JavaScript
    0.07
    .ship
    0.07
    发现
    0.07
     YYYY
    0.07
    ציות
    0.07
    氦
    0.07
    nga
    0.06
    ']}
    0.06
    Activations Density 0.001%

    No Known Activations