© 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. 30-TRANSCODER-HP
    7. 95695
    Prev
    Next
    INDEX
    Explanations

    Code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     effort
    -1.54
    åĬªåĬĽ
    -1.33
     efforts
    -1.30
     Eff
    -1.12
    çļĦåĬªåĬĽ
    -1.09
     ÑĥÑģили
    -0.89
     ëħ¸ëł¥
    -0.81
    -eff
    -0.81
    åĬª
    -0.76
    åĬ³åĬ¨
    -0.74
    POSITIVE LOGITS
    arcy
    0.27
    å±Ģéķ¿
    0.25
    浪漫
    0.25
    .nextInt
    0.24
    peare
    0.24
    ipc
    0.23
    braco
    0.23
    ny
    0.23
    estone
    0.23
    ç©°
    0.23
    Activations Density 0.897%

    No Known Activations