© 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. 9-TRANSCODER-HP
    7. 30376
    Prev
    Next
    INDEX
    Explanations

    crying or eyes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    loquent
    -0.33
    åħ±åĴĮ
    -0.31
    abilia
    -0.28
    usch
    -0.28
     glazed
    -0.27
     republican
    -0.26
     antid
    -0.26
    Falsy
    -0.26
    bum
    -0.26
     leds
    -0.25
    POSITIVE LOGITS
     delegation
    0.28
    ese
    0.28
     DE
    0.26
    ç«ĭæĸ¹
    0.24
    PE
    0.24
    EPS
    0.24
     PEN
    0.24
     exit
    0.24
    deen
    0.24
    space
    0.24
    Activations Density 1.207%

    No Known Activations