© 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. 22932
    Prev
    Next
    INDEX
    Explanations

    leaves

    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
    Blocking
    -0.27
    pace
    -0.27
    æĢĢ
    -0.25
    atar
    -0.25
    æĹłéĻIJ
    -0.25
    å¹³æ°ij
    -0.25
    hold
    -0.25
    ê¼´
    -0.24
    æĹ¥èµ·
    -0.24
    aż
    -0.24
    POSITIVE LOGITS
    æĪĸ许
    0.29
    /head
    0.26
    çŃ¹å¤ĩ
    0.25
     intercept
    0.24
    localized
    0.24
     pne
    0.24
    /icons
    0.24
     headquartered
    0.23
    管çIJĨå±Ģ
    0.23
    spender
    0.23
    Activations Density 0.000%

    No Known Activations