© 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. 35-TRANSCODER-HP
    7. 40220
    Prev
    Next
    INDEX
    Explanations

    location descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    足
    -0.39
     decimal
    -0.31
     durations
    -0.31
     particle
    -0.30
     updates
    -0.29
     resource
    -0.29
     iteration
    -0.29
     responses
    -0.29
     systematic
    -0.28
     parameters
    -0.28
    POSITIVE LOGITS
     Tavern
    0.29
     Basement
    0.28
     Maison
    0.27
     Laurie
    0.27
     Ramos
    0.27
     Riverside
    0.26
     Alumni
    0.26
    Trash
    0.25
     Marseille
    0.25
     Xavier
    0.25
    Activations Density 27.774%

    No Known Activations