© 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. 23-TRANSCODER-HP
    7. 24701
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndo
    -0.28
    <footer
    -0.25
     stacks
    -0.25
    <nav
    -0.24
    readcrumbs
    -0.23
    alse
    -0.23
    çģ£
    -0.23
    ãģ«ãģĹãģ¦
    -0.23
    并ä¸İ
    -0.23
    ضØŃ
    -0.23
    POSITIVE LOGITS
    INET
    0.28
    Č↵
    0.27
    ilies
    0.27
     di
    0.26
    æĹ¥è®°
    0.25
    digit
    0.25
    ays
    0.24
    æľĢæĸ°çļĦ
    0.24
    西åĮ»
    0.24
     '{@
    0.24
    Activations Density 0.008%

    No Known Activations