© 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. 25138
    Prev
    Next
    INDEX
    Explanations

    Broad topics

    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
    uco
    -0.32
    aware
    -0.24
     AUTHOR
    -0.24
    ãĤ´
    -0.24
    hurst
    -0.24
    BO
    -0.24
     iterate
    -0.23
     term
    -0.23
    è§Ħç¨ĭ
    -0.23
    çĥ«
    -0.23
    POSITIVE LOGITS
    ço
    0.27
    è¿ĻæĿ¡
    0.27
    èĬĥ
    0.26
    åľ¨ä¸Ģ个
    0.25
    éĢīæĭ©
    0.25
    æ²
    0.24
     porr
    0.24
    åľ¨è¿Ļ
    0.23
    <Func
    0.23
    è¿Ļç¬Ķ
    0.23
    Activations Density 0.007%

    No Known Activations