© 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. 33-TRANSCODER-HP
    7. 54039
    Prev
    Next
    INDEX
    Explanations

    tw

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     latina
    -0.27
    belt
    -0.26
    umes
    -0.25
     Rac
    -0.25
    йÑĤеÑģÑĮ
    -0.25
    nelle
    -0.24
    çļĦæľĢåIJİä¸Ģ
    -0.23
    urement
    -0.23
     tubes
    -0.23
    =output
    -0.23
    POSITIVE LOGITS
    ide
    0.34
    ang
    0.31
    ided
    0.27
    å®ī
    0.27
    sp
    0.26
     Spurs
    0.26
    amm
    0.25
    为åĩĨ
    0.25
    char
    0.25
    иÑģÑĤ
    0.25
    Activations Density 0.009%

    No Known Activations