© 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. 9455
    Prev
    Next
    INDEX
    Explanations

    Technical code and text

    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
     general
    -1.65
    ä¸ĢèĪ¬
    -1.52
     generally
    -1.51
    general
    -1.29
     geral
    -1.26
     Generally
    -1.22
    -general
    -1.18
     General
    -1.18
     général
    -1.17
    General
    -1.16
    POSITIVE LOGITS
    bv
    0.27
    åĭº
    0.24
    endum
    0.24
    ="?
    0.23
    setContent
    0.23
    å²ij
    0.23
    elope
    0.23
    å®´
    0.23
    -shirt
    0.23
     leaps
    0.23
    Activations Density 0.001%

    No Known Activations