© 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. 41266
    Prev
    Next
    INDEX
    Explanations

    from

    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
    OTE
    -0.28
     lÆ°ng
    -0.27
    ä¸į便
    -0.26
    quete
    -0.26
    æı½
    -0.25
    ç±³å°Ķ
    -0.25
     aren
    -0.25
    浪费
    -0.23
    Stream
    -0.23
     chóng
    -0.23
    POSITIVE LOGITS
    çļĦæ¦Ĥçİĩ
    0.26
    çļĦæĥ³æ³ķ
    0.25
    æ¦Ĥçİĩ
    0.25
     Cô
    0.25
    '||
    0.25
    .ttf
    0.24
    herits
    0.24
    åĬłåĪĨ
    0.24
    uvian
    0.23
    inished
    0.23
    Activations Density 0.417%

    No Known Activations