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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 3262
    Prev
    Next
    INDEX
    Explanations

    Leaders and important figures

    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
    机械设备
    -0.07
     Penny
    -0.07
    在一旁
    -0.07
    _heads
    -0.07
    /N
    -0.07
    (numpy
    -0.06
     Za
    -0.06
     padd
    -0.06
    _gender
    -0.06
    想了想
    -0.06
    POSITIVE LOGITS
     concentrates
    0.07
     dies
    0.06
    フォー
    0.06
    人心
    0.06
    厖
    0.06
     relying
    0.06
    Injected
    0.06
    ダイエット
    0.06
    >")↵
    0.06
     Door
    0.06
    Activations Density 0.027%

    No Known Activations