© 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. 9107
    Prev
    Next
    INDEX
    Explanations

    a

    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
    tes
    -0.28
    ä½įç½®
    -0.26
    æĶ¸
    -0.26
     location
    -0.25
    个ä½ĵ
    -0.25
    æĪ¿åŃIJ
    -0.25
    ;charset
    -0.24
    ensus
    -0.24
    _Generic
    -0.24
    ä¼ĺåĮĸ
    -0.24
    POSITIVE LOGITS
     extensive
    0.28
    agal
    0.27
     university
    0.26
    é«ĺéĢŁåħ¬è·¯
    0.26
    aji
    0.25
    ajor
    0.25
    æĬķ
    0.25
    agara
    0.25
     Sauce
    0.25
     Lat
    0.24
    Activations Density 0.004%

    No Known Activations