© 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. 19-TRANSCODER-HP
    7. 8064
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Desk
    -0.26
    wear
    -0.24
    åºĶåıĬæŶ
    -0.24
    оде
    -0.24
    æŁ¥çľĭæĽ´å¤ļ
    -0.24
    ognito
    -0.24
    mong
    -0.24
    ä½ĵçİ°åľ¨
    -0.24
    ä½Ĩä»ĸ们
    -0.24
    çŀĴ
    -0.23
    POSITIVE LOGITS
    æ°¸
    0.30
    '^
    0.27
    "))č↵
    0.25
    éĻĦåĬł
    0.25
    åıĬåħ¶
    0.25
    "));č↵
    0.24
     eternity
    0.24
    heed
    0.23
    ür
    0.23
     ));č↵
    0.23
    Activations Density 0.044%

    No Known Activations