© 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. 22759
    Prev
    Next
    INDEX
    Explanations

    lactate, rate

    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
    uyo
    -0.27
    åѦåĪ°
    -0.26
    å¼ĢéŨ
    -0.26
    è¿ĻæĿ¡
    -0.25
    lernen
    -0.25
    æĦī
    -0.25
    ening
    -0.24
    asaki
    -0.24
    cher
    -0.24
     extracted
    -0.24
    POSITIVE LOGITS
    -stock
    0.32
     Bett
    0.27
    æ¶īå«Į
    0.26
    odelist
    0.25
    ective
    0.24
     amph
    0.24
    odem
    0.23
     Amph
    0.23
    gone
    0.23
    缸åIJĮçļĦ
    0.23
    Activations Density 0.004%

    No Known Activations