© 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. 56719
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    iola
    -0.30
    èļģ
    -0.29
    igos
    -0.28
    IGO
    -0.28
    chrome
    -0.26
     lens
    -0.25
    åijĬè¯īæĪij们
    -0.25
     lost
    -0.25
     bait
    -0.25
    enor
    -0.25
    POSITIVE LOGITS
     réfé
    0.28
    uhl
    0.28
    Gate
    0.26
    æ¡ĥ
    0.25
    å®ĪæĬ¤
    0.25
    éĢłèĪ¹
    0.25
    èµ·è¯ī
    0.24
    ental
    0.24
     Açık
    0.23
     Duty
    0.23
    Activations Density 0.137%

    No Known Activations