© 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. 18129
    Prev
    Next
    INDEX
    Explanations

    medicinal extracts

    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
    natural
    -0.38
    èĩªçĦ¶
    -0.35
    èĩªçĦ¶èĢĮ
    -0.34
     natural
    -0.34
     PRES
    -0.28
     Natural
    -0.28
    èĩªçĦ¶çķĮ
    -0.27
     pres
    -0.27
    razil
    -0.27
    Ctrl
    -0.27
    POSITIVE LOGITS
    ached
    0.30
    rous
    0.27
    åŃļ
    0.27
    -metal
    0.26
     unf
    0.26
    çļĦåĵģçīĮ
    0.26
     Sag
    0.25
    ainless
    0.25
    åħ¥
    0.25
     finally
    0.24
    Activations Density 1.154%

    No Known Activations