© 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. 31-TRANSCODER-HP
    7. 19230
    Prev
    Next
    INDEX
    Explanations

    excitement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    serious
    -0.34
     serious
    -0.32
     basically
    -0.31
     major
    -0.30
    major
    -0.28
    verity
    -0.27
    æĭĹ
    -0.27
    èĻĶ
    -0.26
     Basically
    -0.26
     essentially
    -0.26
    POSITIVE LOGITS
     terrific
    0.31
     thrilled
    0.30
     fabulous
    0.28
    oso
    0.28
     exc
    0.28
     excited
    0.28
    Exc
    0.27
    _exc
    0.27
    :focus
    0.26
    -exc
    0.26
    Activations Density 19.709%

    No Known Activations