© 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. 23517
    Prev
    Next
    INDEX
    Explanations

    Zero

    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
    èĩĤ
    -0.28
     Mahmoud
    -0.26
    ement
    -0.26
    缮åħī
    -0.25
     passé
    -0.25
    ofile
    -0.25
    elif
    -0.25
    oves
    -0.24
    endif
    -0.24
    raid
    -0.24
    POSITIVE LOGITS
    urger
    0.27
    urred
    0.26
    ä¸įåıĹ
    0.26
    .packet
    0.26
     destiny
    0.25
    æĺ¯éŁ©åĽ½
    0.25
    èĺ¸
    0.25
     clot
    0.24
    åı¦è¡Į
    0.23
    æľ¨èĢ³
    0.23
    Activations Density 0.016%

    No Known Activations