© 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. 24691
    Prev
    Next
    INDEX
    Explanations

    ard

    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
    egas
    -0.32
    oks
    -0.28
    åĴĮå¹³
    -0.27
    ***↵
    -0.26
    rary
    -0.25
    rollers
    -0.25
    req
    -0.25
    pragma
    -0.25
    agram
    -0.24
    eff
    -0.24
    POSITIVE LOGITS
    管çIJĨå·¥ä½ľ
    0.25
    ä¸įå°ı
    0.25
    #endregion
    0.24
    çIJĨä¼ļ
    0.24
    è¯Ŀ
    0.24
    åľ°éģĵ
    0.24
    ized
    0.23
     inspires
    0.23
     trusts
    0.23
     inspire
    0.23
    Activations Density 0.051%

    No Known Activations