© 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. 96232
    Prev
    Next
    INDEX
    Explanations

    medical/scientific contexts

    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
    èĪį
    -0.28
     chlor
    -0.26
    Angular
    -0.26
    èµĽ
    -0.26
    ìĸ´ìĦľ
    -0.26
     Fairfield
    -0.25
    getClient
    -0.25
    ä½ĵ
    -0.24
     sel
    -0.24
    selector
    -0.24
    POSITIVE LOGITS
     pratic
    0.27
    orientation
    0.27
    нем
    0.26
    ina
    0.25
    ides
    0.25
     пÑĢакÑĤи
    0.25
    ORIZ
    0.25
    iname
    0.24
    insk
    0.24
     Orientation
    0.24
    Activations Density 0.011%

    No Known Activations