© 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. 40395
    Prev
    Next
    INDEX
    Explanations

    instructions and disclaimers

    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
    scopic
    -0.27
    implified
    -0.26
     architectural
    -0.25
     infrastructure
    -0.25
    —a
    -0.25
    icient
    -0.25
    ibilit
    -0.24
    ematics
    -0.24
    dashboard
    -0.24
    ellaneous
    -0.24
    POSITIVE LOGITS
     pass
    0.45
     Pass
    0.34
     have
    0.33
     pharm
    0.33
     Need
    0.32
     tell
    0.31
     call
    0.30
     check
    0.30
     be
    0.30
     remember
    0.28
    Activations Density 0.455%

    No Known Activations