© 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. 57297
    Prev
    Next
    INDEX
    Explanations

    Data and programming contexts

    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
    为主é¢ĺçļĦ
    -0.29
    elts
    -0.29
    çļİ
    -0.28
    è²Į
    -0.27
    çļĦ身份
    -0.27
    éŁŃ
    -0.26
    èĤ¤èī²
    -0.26
     ocup
    -0.25
    estre
    -0.25
    è¡Ĺéģĵ
    -0.25
    POSITIVE LOGITS
     IData
    0.30
    æķ°æį®
    0.29
    -data
    0.28
     data
    0.27
    \Migrations
    0.27
    лик
    0.27
    æĦı大
    0.26
    æķ°æį®åĪĨæŀIJ
    0.25
     blazing
    0.25
    -bar
    0.25
    Activations Density 0.009%

    No Known Activations