© 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. 9103
    Prev
    Next
    INDEX
    Explanations

    programming and authentication

    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
     tritur
    -0.24
    æĤ¬æĮĤ
    -0.24
     embedded
    -0.23
    ä¹ĺåĿIJ
    -0.23
    è¿ĽåŁİ
    -0.23
    ç«ĭæ¡Ī
    -0.23
    rum
    -0.23
    èĢIJ
    -0.23
    	atomic
    -0.23
    çļĦèĥ½éĩı
    -0.23
    POSITIVE LOGITS
    æĸ¹å¼ı
    0.31
    ksi
    0.30
     way
    0.28
    æĢ§çĸ¾çĹħ
    0.28
    èĥ½åĬĽå¼º
    0.27
    vided
    0.27
    erties
    0.27
     capability
    0.27
    curve
    0.26
    äºĭçī©
    0.26
    Activations Density 0.022%

    No Known Activations