© 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. 24805
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
    ¡°
    -0.28
    æŶéĹ´ä¸º
    -0.25
    |}↵
    -0.25
    (/^
    -0.23
    esor
    -0.23
    ,ID
    -0.23
    转载请
    -0.23
    orial
    -0.23
    å¤§åĽ½
    -0.23
    _sex
    -0.23
    POSITIVE LOGITS
    mutation
    0.29
    夫
    0.29
    mutable
    0.29
    history
    0.28
    ç§ijæķĻ
    0.28
    plements
    0.27
    Mutable
    0.26
    箫
    0.25
    åºij
    0.25
     Polit
    0.25
    Activations Density 0.004%

    No Known Activations