© 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. 24423
    Prev
    Next
    INDEX
    Explanations

    Ray

    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
    stown
    -0.29
    æľĿ
    -0.28
    触åıĬ
    -0.26
    æµı
    -0.25
    nez
    -0.25
    ç»ĨåĮĸ
    -0.25
     mass
    -0.24
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.24
    éĢł
    -0.24
    æľ¬èĥ½
    -0.23
    POSITIVE LOGITS
    ValuePair
    0.29
    umed
    0.26
    htar
    0.25
    usta
    0.24
    urd
    0.24
    .fromString
    0.24
     unsuccessfully
    0.23
    æ´¾
    0.23
    erde
    0.23
    人æĸĩ
    0.23
    Activations Density 0.012%

    No Known Activations