© 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. 23-TRANSCODER-HP
    7. 23786
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩĩåıĸ
    -0.27
    theon
    -0.27
    pletion
    -0.24
    unkt
    -0.24
     bz
    -0.24
    ogan
    -0.24
    ä¸ĩ家
    -0.24
     though
    -0.23
     ÑĥÑģили
    -0.23
     efforts
    -0.23
    POSITIVE LOGITS
     Sle
    0.30
    幸
    0.27
    =-=-=-=-=-=-=-=-
    0.26
     Supported
    0.26
    Supported
    0.26
    çļĦæĶ¯æĮģ
    0.26
    /red
    0.25
     Confidential
    0.24
     mutable
    0.24
    åĴĮæĶ¯æĮģ
    0.24
    Activations Density 0.067%

    No Known Activations