© 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. 43407
    Prev
    Next
    INDEX
    Explanations

    preventing something from happening

    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
    ate
    -0.33
     being
    -0.33
    being
    -0.28
    éºĿ
    -0.27
    åľĥ
    -0.26
     growth
    -0.26
    家
    -0.26
    prevent
    -0.25
     Mint
    -0.25
    èıĢ
    -0.25
    POSITIVE LOGITS
    Run
    0.26
    åħ·
    0.26
    startIndex
    0.26
    éĢģåĪ°
    0.26
    åĪ»
    0.25
     progressive
    0.25
     dé
    0.25
    Progress
    0.25
     DISPATCH
    0.25
    大åıij
    0.25
    Activations Density 0.000%

    No Known Activations