© 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. 29959
    Prev
    Next
    INDEX
    Explanations

    kins

    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
     bead
    -0.31
     carr
    -0.30
    atr
    -0.28
    ÅŁim
    -0.28
     removeAll
    -0.26
    éħįå¤ĩ
    -0.25
    orne
    -0.25
    åľ°æ¯¯
    -0.25
     %@",
    -0.24
    ateg
    -0.24
    POSITIVE LOGITS
    awns
    0.27
    ä¸ªå·¥ä½ľæĹ¥
    0.27
    æī£
    0.27
    ports
    0.26
    Trading
    0.26
     Contracts
    0.26
    ryn
    0.26
    DMI
    0.25
    BarItem
    0.25
     polls
    0.24
    Activations Density 0.251%

    No Known Activations