© 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 EvalsExportsAPI 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. 57423
    Prev
    Next
    INDEX
    Explanations

    osh

    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
    onet
    -0.07
     magistrate
    -0.07
    positor
    -0.07
     Forecast
    -0.06
     temptation
    -0.06
    inine
    -0.06
     Insurance
    -0.06
     ограни
    -0.06
    劫
    -0.06
    造假
    -0.06
    POSITIVE LOGITS
    根据自己
    0.09
    מיל
    0.08
    ('~
    0.07
    —who
    0.07
     �
    0.07
    kształ
    0.07
    �
    0.07
    )get
    0.07
    Ự
    0.07
    佾
    0.07
    Activations Density 0.001%

    No Known Activations