© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    11. 68962
    Prev
    Next
    INDEX
    Explanations

    identifier

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Php
    -0.08
     Snake
    -0.07
    枫
    -0.07
    rok
    -0.07
     Yoga
    -0.07
    -low
    -0.07
    热水
    -0.07
    efa
    -0.07
     Thor
    -0.07
     Crime
    -0.06
    POSITIVE LOGITS
    市场
    0.07
    𝘪
    0.07
    ائح
    0.06
    ㉯
    0.06
    鿎
    0.06
     ситуации
    0.06
     mattered
    0.06
    责任感
    0.06
    حضور
    0.06
     bacheca
    0.06
    Activations Density 0.017%

    No Known Activations