© 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. 40333
    Prev
    Next
    INDEX
    Explanations

    diagrams and patents

    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
     disastr
    -0.37
     incarcer
    -0.37
     unavoid
    -0.37
    —even
    -0.37
    —it
    -0.36
     imprison
    -0.35
     arrog
    -0.35
    —who
    -0.35
    —but
    -0.35
     impover
    -0.35
    POSITIVE LOGITS
     Extensions
    0.35
     Coordinates
    0.35
     Documentation
    0.34
     Constraints
    0.34
     Dates
    0.34
     Signals
    0.34
     Recipes
    0.33
     Positions
    0.33
     Dependencies
    0.33
     Specifications
    0.33
    Activations Density 12.291%

    No Known Activations