© 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. 24520
    Prev
    Next
    INDEX
    Explanations

    make

    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
    å¤ķ
    -0.28
    åĬĽè¿ĺæĺ¯
    -0.27
    缺
    -0.27
    çļĦä¸Ģç§į
    -0.27
    çļĦ大
    -0.26
    çĥŃçĥĪ
    -0.26
     reap
    -0.25
    Effect
    -0.25
    æĺ¯ä¸Ģç§į
    -0.25
    çļĦä¸Ģ项
    -0.25
    POSITIVE LOGITS
    .Please
    0.27
    eline
    0.26
    inke
    0.26
    @stop
    0.25
     __("
    0.25
    令
    0.25
    NetMessage
    0.24
    æ¼ł
    0.24
    =back
    0.24
    è¿Ļ个èģĮä¸ļ
    0.24
    Activations Density 0.013%

    No Known Activations