© 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. 14-TRANSCODER-HP
    7. 40830
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demean
    -0.31
    antu
    -0.29
    è¤ļ
    -0.27
    adin
    -0.26
    aina
    -0.25
     sonst
    -0.24
    è®¤çľŁ
    -0.24
    ight
    -0.24
    _MR
    -0.24
    é³ķ
    -0.23
    POSITIVE LOGITS
    ossal
    0.28
    åį´ä¸į
    0.27
    åĥıæĺ¯
    0.26
    åı¬åĽŀ
    0.26
     midpoint
    0.26
    å°ıçĶ·åŃ©
    0.25
    æĴ¤ç¦»
    0.24
    ä¸įåĩºæĿ¥
    0.23
     damned
    0.23
    å©´
    0.23
    Activations Density 0.446%

    No Known Activations