© 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. 12-TRANSCODER-HP
    7. 23416
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otten
    -0.26
    .future
    -0.26
    .TXT
    -0.25
     pró
    -0.24
    ÃŃcul
    -0.24
    èįª
    -0.24
     siti
    -0.23
    两çĤ¹
    -0.23
    assin
    -0.23
    ilm
    -0.23
    POSITIVE LOGITS
    &quot
    0.28
    Bus
    0.28
     Bus
    0.27
    为äºĨ让
    0.26
    &gt
    0.26
     mus
    0.25
    Bed
    0.25
    ;.
    0.25
     reg
    0.24
    æ°¸ä¸į
    0.24
    Activations Density 0.034%

    No Known Activations