© 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. 9-TRANSCODER-HP
    7. 29579
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Not in Any Lists

    No Comments

    Negative Logits
     tail
    -0.30
    keit
    -0.25
    æĦŁåıĹåĪ°
    -0.24
    tail
    -0.24
     tighter
    -0.24
     tailor
    -0.24
     tails
    -0.24
     detox
    -0.23
    ONY
    -0.23
     transparency
    -0.23
    POSITIVE LOGITS
    @@
    0.24
    ialis
    0.24
    奴
    0.24
    æ³±
    0.24
    èł
    0.23
    asin
    0.23
    æ©Ħ
    0.23
    Picker
    0.23
    å»ī
    0.22
    çļĦåĬŀæ³ķ
    0.22
    Activations Density 1.691%

    No Known Activations