© 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. 18-TRANSCODER-HP
    7. 89075
    Prev
    Next
    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨ä¸ŃåĽ½
    -0.33
    åľ¨æĹ¥æľ¬
    -0.32
    åľ¨ç¾İåĽ½
    -0.30
    stances
    -0.29
    åľ¨æ¸¸æĪıä¸Ń
    -0.28
    ä¸ŃåĽ½å¸Ĥåľº
    -0.25
    æīĢåľ¨
    -0.25
    åľ¨è¿ĩ渡
    -0.25
    åľ¨
    -0.24
    å¹´ä¸ŃåĽ½
    -0.24
    POSITIVE LOGITS
    nergy
    0.27
    æĸ°å¼Ģ
    0.26
    ruc
    0.25
    머
    0.24
    ç¥ŀå¥ĩ
    0.24
    ober
    0.23
    å¥ĩå¦Ļ
    0.23
     mans
    0.23
    éŨåºĹ
    0.23
    æ
    0.23
    Activations Density 42.967%

    No Known Activations