© 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. 24433
    Prev
    Next
    INDEX
    Explanations

    Bad

    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
    ea
    -0.26
    feito
    -0.26
    õ
    -0.25
    好ä¸į好
    -0.25
    äºĨä¸Ģä¸ĭ
    -0.24
    çļĦçĶ·äºº
    -0.24
    Uploader
    -0.24
    /path
    -0.23
    çļĦ人çĶŁ
    -0.23
    eah
    -0.23
    POSITIVE LOGITS
    istar
    0.27
    åĽĬ
    0.27
    morgan
    0.26
    enci
    0.26
    'Brien
    0.25
    æŀ¯çĩ¥
    0.24
     handleClose
    0.24
    imize
    0.24
    æĮģç»Ń
    0.24
    æİĴéĻ¤
    0.23
    Activations Density 0.073%

    No Known Activations