© 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. 25-TRANSCODER-HP
    7. 108197
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensor
    -0.28
    æķĻå¸Ī
    -0.27
    ç»ıåħ¸
    -0.27
    为ä¾ĭ
    -0.26
    æŀĦ建
    -0.26
     felt
    -0.25
    º«
    -0.25
    èħ¹
    -0.25
    ä¸ºåŁºç¡Ģ
    -0.25
    Assembly
    -0.24
    POSITIVE LOGITS
    æĿ¥åĽŀ
    0.28
    æĹ¶ä»£çļĦ
    0.26
    пÑĢовод
    0.26
     Fore
    0.25
     fore
    0.25
    åĽ½ç«ĭ
    0.25
     Physics
    0.24
    åIJĪä½ľåħ³ç³»
    0.24
    家ãģ®
    0.24
    åįĩåѦ
    0.24
    Activations Density 0.910%

    No Known Activations