© 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. 18274
    Prev
    Next
    INDEX
    Explanations

    Medical/Scientific Research

    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
    绣
    -0.30
    кÑģ
    -0.29
     reven
    -0.27
    elin
    -0.26
    mast
    -0.25
    odb
    -0.25
    kt
    -0.25
    kest
    -0.25
    hear
    -0.25
    elix
    -0.24
    POSITIVE LOGITS
    åı°
    0.27
    DER
    0.27
    ÃŃf
    0.26
    åıĻ
    0.26
    ivamente
    0.25
    çĵ¦
    0.25
    åĬłçĽĸ
    0.24
    èĩº
    0.24
    istani
    0.23
    RSS
    0.23
    Activations Density 0.784%

    No Known Activations