© 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. 14-TRANSCODER-HP
    7. 41269
    Prev
    Next
    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chern
    -0.26
     sudden
    -0.26
    ongs
    -0.26
    骤
    -0.25
    ç®Ķ
    -0.25
     complic
    -0.25
     Specs
    -0.24
    hek
    -0.24
    AMPL
    -0.23
    udden
    -0.23
    POSITIVE LOGITS
    æľīä¸Ģä½į
    0.28
    å»ĵ
    0.28
    igli
    0.26
    快讯
    0.25
     blockSize
    0.25
    cosa
    0.25
    ãģŀ
    0.24
    ä¸į认è¯Ĩ
    0.23
    matchCondition
    0.23
     één
    0.23
    Activations Density 0.117%

    No Known Activations