© 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. 32-TRANSCODER-HP
    7. 42445
    Prev
    Next
    INDEX
    Explanations

    Scientific or authoritative statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plugs
    -0.33
     passes
    -0.33
     peaks
    -0.32
    cams
    -0.31
    uckles
    -0.31
     stacks
    -0.29
    ivas
    -0.29
    stores
    -0.28
     resorts
    -0.28
     hunts
    -0.28
    POSITIVE LOGITS
     qualify
    0.31
     bonded
    0.31
     feel
    0.30
     look
    0.29
     explore
    0.28
     note
    0.28
     operated
    0.28
     realize
    0.27
    Opened
    0.27
     point
    0.27
    Activations Density 0.003%

    No Known Activations