© 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. 15-RESID-POST-AA
    11. 83856
    Prev
    Next
    INDEX
    Explanations

    -compose

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hug
    -0.08
    著
    -0.07
     faux
    -0.07
    針
    -0.07
     relación
    -0.07
    ricula
    -0.07
    lug
    -0.07
    Advisor
    -0.06
     Charity
    -0.06
     الكتاب
    -0.06
    POSITIVE LOGITS
    ⬊
    0.07
     tank
    0.07
     /**
    0.07
    ('.',
    0.07
     снижен
    0.06
    _Inter
    0.06
    .SelectedIndexChanged
    0.06
    stddef
    0.06
    .AutoScale
    0.06
    .State
    0.06
    Activations Density 0.001%

    No Known Activations