© 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. 57916
    Prev
    Next
    INDEX
    Explanations

    varied text snippets

    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
    è¦Ĩ
    -0.34
    åºķ
    -0.33
    çī¹æ´¾
    -0.28
    æī¹
    -0.26
    styles
    -0.25
     Tomas
    -0.25
    ç½®äºİ
    -0.25
    jective
    -0.25
    æīĭæ³ķ
    -0.25
     bottom
    -0.25
    POSITIVE LOGITS
    -feed
    0.26
    çĽijçĿ£æ£ĢæŁ¥
    0.26
    åıĺæĢģ
    0.26
    è¿Ļ个è¯į
    0.25
    VIS
    0.25
     visualization
    0.25
     incentive
    0.24
    PATH
    0.24
    æĬµæĬĹåĬĽ
    0.24
    iro
    0.24
    Activations Density 0.007%

    No Known Activations