© 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. 23671
    Prev
    Next
    INDEX
    Explanations

    tall

    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¸ĢæĿ¡
    -0.31
    quo
    -0.29
    æĻ®åıĬ
    -0.27
    HU
    -0.27
    ä¸Ģ款
    -0.26
    quip
    -0.26
     stuck
    -0.26
     Pak
    -0.26
    ä¸Ģåī¯
    -0.26
    æĭĸ
    -0.25
    POSITIVE LOGITS
    odelist
    0.30
    eref
    0.29
    íĿIJ
    0.27
    åıij声
    0.26
    éĶ¾
    0.25
    gráfico
    0.25
    ndon
    0.24
    .yy
    0.24
    ichel
    0.24
    kwargs
    0.24
    Activations Density 0.000%

    No Known Activations