© 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. 43092
    Prev
    Next
    INDEX
    Explanations

    Starts of questions/writing

    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
    sec
    -0.30
    SEC
    -0.28
    ze
    -0.28
    西æ¹ĸ
    -0.28
     decreased
    -0.28
     SEC
    -0.27
    ä¸Ģç¬ij
    -0.27
    opa
    -0.27
    secs
    -0.27
    å¡ŀ
    -0.26
    POSITIVE LOGITS
    emonic
    0.30
     about
    0.28
    åįģæĿ¡
    0.27
    åħŃåįģ
    0.27
    åįģåħŃ
    0.26
     thirty
    0.26
     ten
    0.25
    åįģä¸īæĿ¡
    0.25
    edom
    0.24
     halfway
    0.24
    Activations Density 0.000%

    No Known Activations