© 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. 40645
    Prev
    Next
    INDEX
    Explanations

    human

    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
    æŃ¥
    -0.32
    æĿľ
    -0.29
    intr
    -0.25
    她们
    -0.25
    她çļĦ
    -0.24
     sealing
    -0.24
    .hxx
    -0.23
     dziÅĽ
    -0.23
    iances
    -0.23
    CTX
    -0.23
    POSITIVE LOGITS
    each
    0.25
    åı¯ä»¥æĬĬ
    0.25
    abyrinth
    0.25
    ajes
    0.25
     citizen
    0.25
    que
    0.24
     plat
    0.24
     apl
    0.24
    ä¸ı
    0.24
     canc
    0.24
    Activations Density 0.067%

    No Known Activations