© 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. 30-TRANSCODER-HP
    7. 96302
    Prev
    Next
    INDEX
    Explanations

    all

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refill
    -0.30
    æķ°åѦ
    -0.29
    çī©ç§į
    -0.28
     discharged
    -0.28
    æĪij说
    -0.27
    æŁ¿
    -0.27
    æ´»è·ĥ
    -0.27
     sport
    -0.27
    æ¯ķä¸ļ
    -0.26
    æĬµè¾¾
    -0.26
    POSITIVE LOGITS
     core
    0.39
    æł¸å¿ĥ
    0.35
    core
    0.32
    _core
    0.31
     Core
    0.31
    æł¸å¿ĥåĮº
    0.30
    Core
    0.29
    	core
    0.29
     interests
    0.28
    chal
    0.27
    Activations Density 0.101%

    No Known Activations