© 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. 39155
    Prev
    Next
    INDEX
    Explanations

    awards and honors

    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
     sign
    -0.28
     notice
    -0.28
    å½ĵåį³
    -0.27
     collar
    -0.27
     label
    -0.27
     chant
    -0.26
     granted
    -0.26
     note
    -0.26
     trope
    -0.26
    anh
    -0.26
    POSITIVE LOGITS
     TripAdvisor
    0.30
     Editors
    0.29
    systems
    0.28
     Systems
    0.28
    _processors
    0.28
    drivers
    0.28
     Holmes
    0.27
     Drivers
    0.27
     Veronica
    0.27
     DHS
    0.27
    Activations Density 8.473%

    No Known Activations