© 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. 57792
    Prev
    Next
    INDEX
    Explanations

    names

    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
    -0.31
    Expiration
    -0.27
    alse
    -0.26
    åIJ¬å®Į
    -0.25
    åħ¨åľº
    -0.24
     disp
    -0.24
    ê´Ħ
    -0.24
    æĿ¡æ¬¾
    -0.24
    wait
    -0.24
     expired
    -0.23
    POSITIVE LOGITS
    åij½
    0.28
    æľīä¸Ģå®ļçļĦ
    0.27
    etics
    0.27
    duino
    0.25
    æľĢåIJİä¸Ģ次
    0.25
     fortunate
    0.25
    oir
    0.24
    æĪIJ人
    0.24
    iban
    0.24
    ucas
    0.24
    Activations Density 0.012%

    No Known Activations