© 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. 27-TRANSCODER-HP
    7. 8643
    Prev
    Next
    INDEX
    Explanations

    iny

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    第ä¸ĢèĬĤ
    -0.28
    asion
    -0.27
    ypse
    -0.26
    cent
    -0.25
    å®ĮæĪIJåIJİ
    -0.25
    æĮ¤
    -0.25
    sole
    -0.25
     faint
    -0.24
    antas
    -0.24
     transfer
    -0.24
    POSITIVE LOGITS
    åħ¨ç¤¾ä¼ļ
    0.29
    礼
    0.26
    åIJĦåįķä½į
    0.26
    iego
    0.25
    åħ¨ä½ĵ
    0.24
    iniz
    0.24
    Microsoft
    0.24
    éĥ½å·²ç»ı
    0.24
    IOR
    0.23
    鼶件
    0.23
    Activations Density 0.025%

    No Known Activations