© 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. 58055
    Prev
    Next
    INDEX
    Explanations

    Information or instructions

    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
     onwards
    -0.27
     oath
    -0.26
    æµ£
    -0.25
    .backward
    -0.25
    OTES
    -0.25
     ÑģвÑıз
    -0.25
    å°ıåŃIJ
    -0.24
    æĸ¯å¡Ķ
    -0.24
    à¸ķรà¸ĩ
    -0.24
     lens
    -0.24
    POSITIVE LOGITS
    èµ°
    0.26
    .tk
    0.25
    itin
    0.25
    èµ°ä¸Ĭ
    0.25
     sortable
    0.25
    immers
    0.24
     ваÑĢи
    0.24
    paste
    0.24
    øy
    0.24
     available
    0.24
    Activations Density 0.006%

    No Known Activations