© 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. 42556
    Prev
    Next
    INDEX
    Explanations

    time

    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
     around
    -0.28
    occasion
    -0.26
    itter
    -0.26
    åĽ´ç»ķ
    -0.26
    DAQ
    -0.26
     asympt
    -0.25
    tep
    -0.25
    ptive
    -0.24
    hti
    -0.24
     alike
    -0.24
    POSITIVE LOGITS
     may
    0.33
     appears
    0.33
     sure
    0.31
     does
    0.30
     simply
    0.29
     seldom
    0.28
    å¾Īç®Ģåįķ
    0.27
    ,:,
    0.27
     simplement
    0.26
     жÑĥÑĢ
    0.26
    Activations Density 0.002%

    No Known Activations