© 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. 57908
    Prev
    Next
    INDEX
    Explanations

    upper or lower

    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
     sup
    -0.31
    æ©Łæ§ĭ
    -0.29
    rome
    -0.28
    .Span
    -0.28
    å®Įæķ´æĢ§
    -0.27
    æľºæŀĦ
    -0.26
     tops
    -0.26
    uai
    -0.25
    mmas
    -0.25
    顶å±Ĥ
    -0.24
    POSITIVE LOGITS
    åıĺåİĭ
    0.32
    >No
    0.28
    (piece
    0.26
    诱
    0.25
    骨
    0.24
    anto
    0.23
    åĭ¿
    0.23
    åIJ¸
    0.23
    lectric
    0.23
     Frid
    0.23
    Activations Density 0.005%

    No Known Activations