© 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. 95978
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     organised
    -0.29
    .Misc
    -0.27
    vla
    -0.26
    è¡Įç¨ĭ
    -0.26
    ITE
    -0.26
    å®ŀä½ĵ
    -0.26
     organisation
    -0.25
    stick
    -0.24
    ä½ĵåĨħ
    -0.24
    ä¸Ńè¶ħ
    -0.24
    POSITIVE LOGITS
     khóa
    0.26
     equilibrium
    0.25
    amento
    0.25
    uencia
    0.25
    æµ®
    0.24
    ä¸Ģ次
    0.24
    in
    0.24
    inan
    0.23
    borough
    0.23
    num
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.