© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23746
    Prev
    Next
    INDEX
    Explanations

    magnitude

    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
    -tech
    -0.26
     rankings
    -0.25
    æİĴè¡Įæ¦ľ
    -0.25
     excitement
    -0.25
    itan
    -0.24
    -trained
    -0.23
     robots
    -0.23
    ä¸Ģç¬ij
    -0.23
    pop
    -0.23
    说æĺ¯
    -0.23
    POSITIVE LOGITS
    Ļ¨
    0.27
    YW
    0.27
    conditionally
    0.26
    conditional
    0.25
     unconditional
    0.25
    ä»Ĭ
    0.24
     compared
    0.24
    UCCESS
    0.24
    tings
    0.23
    according
    0.23
    Activations Density 0.006%

    No Known Activations