© 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. 9232
    Prev
    Next
    INDEX
    Explanations

    computer hardware

    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
    edium
    -0.31
     programmed
    -0.30
     segregated
    -0.27
     Programming
    -0.26
    纯
    -0.26
     amb
    -0.26
    ghost
    -0.26
    иÑĢа
    -0.24
    compound
    -0.24
    åĪĨ
    -0.24
    POSITIVE LOGITS
    åĴ
    0.27
     gaze
    0.26
     eye
    0.26
    æīĵåį°æľº
    0.26
    ä¹ĺ
    0.26
    <Props
    0.26
     Eye
    0.25
    éķľå¤´
    0.25
     printer
    0.25
    woke
    0.25
    Activations Density 0.007%

    No Known Activations