© 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
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 9154
    Prev
    Next
    INDEX
    Explanations

    fluorescence and luminescence

    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
    ropri
    -0.28
     once
    -0.26
     hosp
    -0.25
    ä¸Ģåı¥
    -0.25
    èĢģ太太
    -0.25
     lub
    -0.25
     instantaneous
    -0.24
    adier
    -0.24
    atrice
    -0.24
    çŀ¬éĹ´
    -0.24
    POSITIVE LOGITS
    gil
    0.34
    pig
    0.27
    quin
    0.27
    åĬ¨çĶŁæĪIJ
    0.27
     visuals
    0.26
     doGet
    0.25
    pering
    0.25
     entrances
    0.25
    chin
    0.24
    enticated
    0.24
    Activations Density 0.013%

    No Known Activations