© 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. 27-TRANSCODER-HP
    7. 8413
    Prev
    Next
    INDEX
    Explanations

    games, contests, and groups

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.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»·
    -0.29
    ijken
    -0.27
    纲
    -0.26
     пом
    -0.26
    ä»İäºĭ
    -0.25
     politics
    -0.25
    æ²IJ
    -0.25
    æŶåĪ»
    -0.25
    æľīä¸Ģä½į
    -0.25
     momentum
    -0.25
    POSITIVE LOGITS
    ç¬ĶèĢħ
    0.31
    ãĤ°ãĥ«ãĥ¼ãĥĹ
    0.28
     groups
    0.28
    äºĮåŃĹ
    0.27
    ossal
    0.27
     Groups
    0.27
     Trio
    0.26
    /Desktop
    0.26
    olute
    0.26
    Groups
    0.26
    Activations Density 0.002%

    No Known Activations