© 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. 2858
    Prev
    Next
    INDEX
    Explanations

    short time periods

    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
    änger
    -0.07
    ند
    -0.07
    ną
    -0.07
    ሪ
    -0.07
    栉
    -0.07
    ertext
    -0.07
    انب
    -0.07
    несен
    -0.07
    发文
    -0.07
    穗
    -0.07
    POSITIVE LOGITS
    (model
    0.07
    ycles
    0.06
     ц
    0.06
    [K
    0.06
     futures
    0.06
     kra
    0.06
     ceremonial
    0.06
    �니다
    0.06
    etas
    0.06
    .black
    0.06
    Activations Density 0.101%

    No Known Activations