© 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. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24704
    Prev
    Next
    INDEX
    Explanations

    Explaining or listing

    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
    oload
    -0.30
     пÑĢоÑģ
    -0.28
    ä¸Ģ个éĹ®é¢ĺ
    -0.28
    满
    -0.27
    ä¸Ģ个å°ı
    -0.26
    å°ıæŶ
    -0.25
    ersions
    -0.25
    累计
    -0.25
    VISIBLE
    -0.25
    人家
    -0.25
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.31
    ä¸ĭåĪĹ
    0.31
    ize
    0.29
    aling
    0.28
     below
    0.27
    ise
    0.27
    ä¸ĭéĿ¢
    0.26
    åħļå§Ķ
    0.26
     following
    0.25
    åIJĦ大
    0.25
    Activations Density 0.002%

    No Known Activations