© 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. 9059
    Prev
    Next
    INDEX
    Explanations

    scientific details

    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
     redund
    -0.29
    æľĭåıĭ们
    -0.25
     sane
    -0.25
    _dicts
    -0.25
    éħ°
    -0.25
     regenerated
    -0.25
     guessed
    -0.24
    å¼¹
    -0.24
     locations
    -0.24
     ages
    -0.24
    POSITIVE LOGITS
    à¹Ħล
    0.32
    çĮĽ
    0.27
    ahead
    0.25
     véritable
    0.25
    ãģ¾ãģ¾
    0.25
    Ana
    0.24
    æ²»å®ī
    0.24
    Execution
    0.24
     Surgery
    0.24
    ration
    0.23
    Activations Density 0.006%

    No Known Activations