© 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. 43018
    Prev
    Next
    INDEX
    Explanations

    foreign 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
    ->{$
    -0.27
    urances
    -0.25
    ilde
    -0.24
    urette
    -0.24
    ARRIER
    -0.24
    allo
    -0.24
    urent
    -0.24
    ormap
    -0.24
    aravel
    -0.23
    èĤĮ
    -0.23
    POSITIVE LOGITS
    اØ
    0.27
    å¤Ħæĸ¹
    0.26
    çļĦä¸Ģç§į
    0.25
    æĻĴ
    0.25
     Br
    0.25
    产åĩº
    0.25
    ses
    0.24
    ansion
    0.24
    ski
    0.24
    æĹģ
    0.24
    Activations Density 0.009%

    No Known Activations