© 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. 107688
    Prev
    Next
    INDEX
    Explanations

    code and foreign languages

    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
     any
    -0.34
    æľīä»»ä½ķ
    -0.32
    ä»»ä½ķæŶåĢĻ
    -0.31
    (any
    -0.29
    any
    -0.28
    ä»»ä½ķ
    -0.28
     anywhere
    -0.27
     anything
    -0.26
    -any
    -0.26
    ä¹ĭäºĭ
    -0.26
    POSITIVE LOGITS
    olare
    0.32
    å²ĺ
    0.27
     nä
    0.26
     percussion
    0.25
    flip
    0.25
    åĻ¨æ¢°
    0.24
    ç»ıè´¹
    0.24
    errick
    0.24
    è£ħå¤ĩ
    0.24
     irresistible
    0.24
    Activations Density 0.040%

    No Known Activations