© 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. 11-RESID-POST-AA
    11. 96515
    Prev
    Next
    INDEX
    Explanations

    scrum

    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
    apesh
    -0.07
    _PE
    -0.06
     вполне
    -0.06
     bibliography
    -0.06
     рассмат
    -0.06
    Eu
    -0.06
    =None
    -0.05
    (be
    -0.05
    相见
    -0.05
     impe
    -0.05
    POSITIVE LOGITS
     необходим
    0.08
     rows
    0.08
    NSNotification
    0.07
    싀
    0.07
     risen
    0.07
     wys
    0.07
    ثير
    0.07
    OKEN
    0.07
    .Remote
    0.07
    нии
    0.07
    Activations Density 0.001%

    No Known Activations