© 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. 24-TRANSCODER-HP
    7. 150443
    Prev
    Next
    INDEX
    Explanations

    Foreign and storm words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _accepted
    -0.28
     intuit
    -0.28
    åĪĿäºĮ
    -0.26
     Viewing
    -0.26
    纪念
    -0.25
    ä¸Ĭ线
    -0.25
    è¯ļæĦı
    -0.25
    两æīĭ
    -0.24
    æ¯ı个人çļĦ
    -0.24
    亲æĪļ
    -0.24
    POSITIVE LOGITS
    é£İ鼨
    0.35
     storms
    0.32
     floods
    0.31
    çģ¾éļ¾
    0.30
    åı°é£İ
    0.30
    èĩªçĦ¶çģ¾å®³
    0.29
    vak
    0.29
     storm
    0.29
    鼨
    0.28
    éĻ©
    0.28
    Activations Density 0.107%

    No Known Activations