© 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. 9-TRANSCODER-HP
    7. 29602
    Prev
    Next
    INDEX
    Explanations

    Gan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĦı大
    -0.26
    éĩį
    -0.26
    noinspection
    -0.26
    æĭĽæĶ¶
    -0.25
    .assign
    -0.24
    .abstract
    -0.24
    alten
    -0.24
    rowave
    -0.23
    åĿ¨
    -0.23
    acht
    -0.23
    POSITIVE LOGITS
    è´´
    0.30
    å±Ĥå±Ĥ
    0.28
    eti
    0.27
    è²¼
    0.26
     benchmarks
    0.26
    ä¸Ģä¸Ŀ
    0.26
     envy
    0.26
    /pp
    0.25
    er
    0.24
    纵横
    0.24
    Activations Density 1.044%

    No Known Activations