© 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. 58160
    Prev
    Next
    INDEX
    Explanations

    lungs

    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
    ä¾ĭ
    -0.27
    <head
    -0.25
    姮
    -0.24
    ç»Ļ她
    -0.24
    æ©
    -0.24
    è¡¥
    -0.24
    çĶŁçIJĨ
    -0.24
     legitim
    -0.24
     channel
    -0.24
    èĵĿèī²
    -0.24
    POSITIVE LOGITS
     billed
    0.28
    leccion
    0.28
    ption
    0.27
    atchet
    0.27
     molds
    0.26
     disappearance
    0.25
    icolon
    0.25
    @SuppressWarnings
    0.25
    odate
    0.25
    nock
    0.25
    Activations Density 0.005%

    No Known Activations