© 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. 41862
    Prev
    Next
    INDEX
    Explanations

    say "century"

    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
    åħ«
    -0.27
    èįª
    -0.25
    çłĸ
    -0.25
    æİ¥æĶ¶
    -0.24
    æĭĸ
    -0.24
     tir
    -0.24
    çľĭå¾Ĺ
    -0.24
    è½»è½»åľ°
    -0.24
    ä¸ī代
    -0.23
    è¡Į使
    -0.23
    POSITIVE LOGITS
    oose
    0.33
     syll
    0.28
    oice
    0.26
    enity
    0.26
    èĩªåľ¨
    0.25
    oop
    0.25
    ringe
    0.25
    CRE
    0.25
     SLOT
    0.24
    车
    0.24
    Activations Density 0.001%

    No Known Activations