© 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. 32-TRANSCODER-HP
    7. 41727
    Prev
    Next
    INDEX
    Explanations

    Or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fork
    -0.30
    etched
    -0.30
    edly
    -0.27
    elib
    -0.27
     AMC
    -0.27
    .SIG
    -0.26
     Signature
    -0.26
    âķĿ
    -0.25
    etsk
    -0.24
     Slide
    -0.24
    POSITIVE LOGITS
    çļĦçłĶåıij
    0.30
    åĿ¡
    0.29
    缸
    0.27
    åIJĪæ³ķ
    0.26
    æĬĽ
    0.26
     Rue
    0.25
    æĬ¥
    0.24
    çļĦè§Ĵèī²
    0.24
    -collapse
    0.24
    isNaN
    0.24
    Activations Density 0.004%

    No Known Activations