© 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. 24012
    Prev
    Next
    INDEX
    Explanations

    not

    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
    让ä»ĸ们
    -0.29
     hij
    -0.29
    /licenses
    -0.28
    æIJŃ
    -0.27
    fü
    -0.26
     rel
    -0.26
     ál
    -0.25
     enc
    -0.25
     maç
    -0.25
    éĢł
    -0.25
    POSITIVE LOGITS
    reading
    0.26
    æľįåĬ¡æľºæŀĦ
    0.26
     SW
    0.25
    ç»ıæµİæĬĢæľ¯
    0.25
    ãģ©
    0.25
    ative
    0.25
     trusted
    0.25
     horn
    0.24
    oram
    0.24
    被è§Ĩ为
    0.24
    Activations Density 0.806%

    No Known Activations