© 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. 40806
    Prev
    Next
    INDEX
    Explanations

    prime and composite numbers

    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
    æ¿ij
    -0.28
    ä¸Ńå°ı
    -0.27
    sworth
    -0.25
    æĭ¨
    -0.25
    asa
    -0.25
    LOS
    -0.24
    InterruptedException
    -0.24
    iores
    -0.24
    ASA
    -0.24
    è§Ĩ
    -0.24
    POSITIVE LOGITS
    ç»ĵæŀĦæĢ§
    0.27
    anker
    0.26
    .Syntax
    0.26
     hak
    0.26
     fortn
    0.26
    æľĢåIJİä¸Ģ次
    0.25
    &T
    0.25
    onde
    0.25
    ORAGE
    0.25
    [table
    0.25
    Activations Density 0.726%

    No Known Activations