© 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. 96105
    Prev
    Next
    INDEX
    Explanations

    fractions and 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
    illary
    -0.28
    太å°ij
    -0.26
    -UA
    -0.26
    observation
    -0.26
    allax
    -0.25
    imeter
    -0.25
    ç»´å¥ĩ
    -0.25
     observation
    -0.25
    amic
    -0.25
    uristic
    -0.25
    POSITIVE LOGITS
    ogs
    0.28
     curt
    0.27
    èĥľ
    0.27
    à¹ģà¸ģ
    0.25
    à¸Ńย
    0.25
    YYY
    0.25
     fifth
    0.24
     sinh
    0.24
     live
    0.24
    YO
    0.24
    Activations Density 0.883%

    No Known Activations