© 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. 8979
    Prev
    Next
    INDEX
    Explanations

    plant

    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
     pint
    -0.27
     POP
    -0.26
    vard
    -0.26
    ifetime
    -0.26
     shaving
    -0.26
     cord
    -0.26
    åľ¨çĶŁæ´»ä¸Ń
    -0.26
     Merc
    -0.26
    ç²Ĵ
    -0.26
    otine
    -0.25
    POSITIVE LOGITS
    íĨµ
    0.26
    é¢Ľ
    0.25
     sede
    0.24
    ATES
    0.24
    ä¸Ģå®ļçļĦ
    0.24
     borderTop
    0.24
    <thead
    0.23
    (video
    0.23
    éĺĶ
    0.23
    idia
    0.23
    Activations Density 0.004%

    No Known Activations