© 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. 20-TRANSCODER-HP
    7. 130045
    Prev
    Next
    INDEX
    Explanations

    Prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dens
    -0.29
    ä»»ä½ķ
    -0.28
    ä»»ä½ķ人
    -0.27
    ä»»ä½ķä¸Ģ个
    -0.27
    anc
    -0.27
     any
    -0.26
     ANY
    -0.26
    åīIJ
    -0.25
     cualquier
    -0.25
     qualquer
    -0.25
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.29
    è¿Ļç¯ĩ
    0.26
    æıIJä¾ĽæĽ´å¤ļ
    0.25
     Bring
    0.25
    turned
    0.25
    带æĿ¥æĽ´å¤ļ
    0.25
    åħ»æĪIJ
    0.24
    affected
    0.24
    åĿŁ
    0.24
     Nur
    0.24
    Activations Density 41.414%

    No Known Activations