© 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. 43590
    Prev
    Next
    INDEX
    Explanations

    Various Languages/Uncommon Words

    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
    她çļĦ
    -0.40
    æĪij们çļĦ
    -0.37
    ä½łçļĦ
    -0.36
    æĪijçļĦ
    -0.33
    æĤ¨çļĦ
    -0.31
    å®ĥçļĦ
    -0.30
     your
    -0.29
    ä»ĸçļĦ
    -0.28
    atus
    -0.28
     our
    -0.28
    POSITIVE LOGITS
     pert
    0.29
    éľĸ
    0.27
     il
    0.26
    èľ»
    0.25
    ÑĦе
    0.25
     Pert
    0.25
    bern
    0.24
    ber
    0.24
    çī¹æ´¾åijĺ
    0.24
     i
    0.24
    Activations Density 0.002%

    No Known Activations