© 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. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162928
    Prev
    Next
    INDEX
    Explanations

    Fighting/advocacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conversion
    -0.26
    å¼Ģå¹ķå¼ı
    -0.26
    ç²¾æ¹Ľ
    -0.26
     dece
    -0.25
    ä¸ĭæīĭ
    -0.25
    æľ¬ç½ijç«Ļ
    -0.24
    çħ§é¡¾
    -0.24
    za
    -0.24
     conversion
    -0.24
    conversion
    -0.24
    POSITIVE LOGITS
    .vol
    0.29
    æĶ¹éĿ©
    0.28
    dif
    0.28
    Ĭ¶
    0.27
    волÑĮ
    0.25
     reform
    0.25
    pike
    0.25
     gag
    0.25
    want
    0.25
    벨
    0.25
    Activations Density 0.005%

    No Known Activations