© 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. 15-RESID-POST-AA
    11. 121052
    Prev
    Next
    INDEX
    Explanations

    network configuration

    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
    发展方向
    -0.08
     remedies
    -0.07
    걜
    -0.07
    йти
    -0.07
    exercise
    -0.07
    liśmy
    -0.07
    excel
    -0.07
    无线电
    -0.06
    贡献力量
    -0.06
    tas
    -0.06
    POSITIVE LOGITS
    (strict
    0.09
    アル
    0.07
     preço
    0.07
    (InputStream
    0.07
    (enum
    0.07
     courte
    0.07
    _OVER
    0.07
     piger
    0.07
    .Unique
    0.07
    舌
    0.07
    Activations Density 0.065%

    No Known Activations