© 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. 23005
    Prev
    Next
    INDEX
    Explanations

    traffic

    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
    ä¸Ģä¸ĭ
    -0.29
    Span
    -0.27
     performing
    -0.27
    渡
    -0.26
    ble
    -0.26
    æĸ¹æ¡Ī
    -0.25
     Red
    -0.25
    Red
    -0.25
    8
    -0.24
     scheme
    -0.24
    POSITIVE LOGITS
    antal
    0.30
    pert
    0.30
     Pert
    0.28
    eah
    0.28
    igital
    0.27
     Templ
    0.27
    ÙĤÙĬÙĤØ©
    0.26
    综
    0.26
     Hayden
    0.26
    AGR
    0.26
    Activations Density 0.000%

    No Known Activations