© 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. 41852
    Prev
    Next
    INDEX
    Explanations

    non-English 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
    istol
    -0.29
     lul
    -0.28
    Iron
    -0.28
    iber
    -0.27
     dol
    -0.27
    ivalence
    -0.27
    ikh
    -0.27
    hips
    -0.27
    ilateral
    -0.25
    issement
    -0.25
    POSITIVE LOGITS
    硬
    0.28
     hard
    0.26
    éħ®
    0.26
    æݧåĪ¶åĻ¨
    0.25
     blindly
    0.25
    åī¯å¸Ĥéķ¿
    0.25
    aday
    0.24
    æĿ³
    0.24
    æµģ
    0.24
    æľ¬è½®
    0.24
    Activations Density 0.000%

    No Known Activations