© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 44201
    Prev
    Next
    INDEX
    Explanations

    replace

    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
    Negative Logits
    è¦ģä¹Ī
    -0.29
    åĢĴéľī
    -0.27
    Either
    -0.27
    Synopsis
    -0.27
    åħ¬çĽĬæĢ§
    -0.26
     sorte
    -0.26
    åIJĮå¿ĥ
    -0.26
     guesses
    -0.26
     soit
    -0.25
    åį·
    -0.25
    POSITIVE LOGITS
    ifest
    0.27
    idf
    0.27
    frey
    0.27
    å±¥
    0.26
     medical
    0.26
     medically
    0.26
    ))->
    0.25
    Clr
    0.25
     Factory
    0.24
     anesthesia
    0.24
    Activations Density 0.002%

    No Known Activations