© 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. 14-TRANSCODER-HP
    7. 41163
    Prev
    Next
    INDEX
    Explanations

    garlic and/or "Gar"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eken
    -0.27
    icing
    -0.26
    .Typed
    -0.26
    俯
    -0.25
    .cent
    -0.25
    å¥ij
    -0.24
     humanity
    -0.24
    elen
    -0.24
    ingen
    -0.24
     catch
    -0.24
    POSITIVE LOGITS
    InitialState
    0.30
    æľīä¿¡å¿ĥ
    0.29
    åħį
    0.28
     Madden
    0.27
    èij±
    0.26
    åºĶæĶ¶
    0.25
     theirs
    0.25
    ÑĮеÑĢ
    0.25
    Dig
    0.24
    ä¸ĩæĪ·
    0.24
    Activations Density 0.274%

    No Known Activations