© 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. 20-TRANSCODER-HP
    7. 107750
    Prev
    Next
    INDEX
    Explanations

    health-related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igious
    -0.28
     constant
    -0.26
    chied
    -0.26
    ductor
    -0.25
     membr
    -0.25
    ients
    -0.24
    rück
    -0.24
    ordova
    -0.24
     поÑģÑĤоÑıн
    -0.23
    imestone
    -0.23
    POSITIVE LOGITS
    omo
    0.28
     Annual
    0.27
     Visible
    0.26
    results
    0.26
    plates
    0.26
    以人æ°ij为
    0.26
    Results
    0.25
    æľĪ
    0.25
    &e
    0.25
     results
    0.25
    Activations Density 12.630%

    No Known Activations