© 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. 23683
    Prev
    Next
    INDEX
    Explanations

    voluntary, involuntary

    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
    åĴ«
    -0.27
    oure
    -0.27
    èł¡
    -0.26
    aptcha
    -0.26
     wishing
    -0.25
    Bed
    -0.25
    WXYZ
    -0.25
     ble
    -0.25
    Implementation
    -0.24
    schemas
    -0.24
    POSITIVE LOGITS
    addir
    0.29
    åħįè´£
    0.29
    è¡Į车
    0.26
     Tig
    0.25
     movements
    0.25
    mov
    0.24
    ogan
    0.24
    æįİ
    0.24
    hu
    0.24
     arc
    0.23
    Activations Density 0.012%

    No Known Activations