© 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. 29992
    Prev
    Next
    INDEX
    Explanations

    asterisk/star

    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
    ilot
    -0.30
    æİ¥
    -0.27
    Means
    -0.26
    份
    -0.26
    èĮ«
    -0.25
    æĦŁè§ī
    -0.25
    第ä¸ĢæĿ¡
    -0.25
    Dod
    -0.25
    AndView
    -0.25
    ngo
    -0.25
    POSITIVE LOGITS
    Pin
    0.31
    reten
    0.28
     SIP
    0.28
    -inv
    0.26
    åĢļ
    0.26
     Pin
    0.26
     subsid
    0.25
    pin
    0.25
    akening
    0.25
    fly
    0.25
    Activations Density 3.500%

    No Known Activations