© 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. 25-TRANSCODER-HP
    7. 108455
    Prev
    Next
    INDEX
    Explanations

    obvious, 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_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edException
    -0.27
    iry
    -0.27
    edImage
    -0.26
    è¯Ŀ说
    -0.25
     sắc
    -0.25
    enti
    -0.25
    iveness
    -0.25
    à¸Ńม
    -0.24
    å£°éŁ³
    -0.23
    íĸ¥
    -0.23
    POSITIVE LOGITS
     obvious
    0.31
    ç®Ģåįķ
    0.28
     straightforward
    0.27
    æ¯Ķè¾ĥç®Ģåįķ
    0.26
    åIJIJ
    0.26
     rep
    0.25
    对çĿĢ
    0.25
    åĸ·æ¶Ĥ
    0.24
    åĬĽè¿ĺæĺ¯
    0.24
     simple
    0.24
    Activations Density 1.023%

    No Known Activations