© 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. 95656
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    _ERR
    -0.25
    ä»Ģä¹Īæł·
    -0.25
    =pos
    -0.25
    âĦĴ
    -0.23
    Authors
    -0.23
    ä¼ģä¸ļ管çIJĨ
    -0.23
     \/
    -0.23
    tern
    -0.22
    .Theme
    -0.22
    ers
    -0.22
    POSITIVE LOGITS
    åĩłä¸ª
    0.79
    两个
    0.77
    å¤ļ个
    0.75
     several
    0.68
    ä¸ī个
    0.67
     two
    0.66
     multiple
    0.65
    åħ©åĢĭ
    0.65
    åħŃ个
    0.64
    å¹¾åĢĭ
    0.63
    Activations Density 0.903%

    No Known Activations