© 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. 96323
    Prev
    Next
    INDEX
    Explanations

    seasons

    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
    åħĭæĸ¯
    -0.28
    åij½
    -0.26
    validated
    -0.26
     WEEK
    -0.26
    igators
    -0.25
    åĻªéŁ³
    -0.25
    åĹĵ
    -0.25
     weekly
    -0.24
    éĿ³
    -0.24
    _UNUSED
    -0.24
    POSITIVE LOGITS
     fall
    0.38
     early
    0.36
     earliest
    0.34
    fall
    0.33
     late
    0.32
     spring
    0.31
     force
    0.30
     Fall
    0.29
    æĶ¶
    0.29
     rise
    0.28
    Activations Density 0.895%

    No Known Activations