© 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. 33-TRANSCODER-HP
    7. 53694
    Prev
    Next
    INDEX
    Explanations

    oral hygiene

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hy
    -0.33
     Hy
    -0.31
    Hy
    -0.30
     Hydra
    -0.29
    åį«çĶŁ
    -0.29
     hygiene
    -0.29
     hid
    -0.27
    æ¡¥
    -0.27
    hy
    -0.26
     Proceed
    -0.25
    POSITIVE LOGITS
    æĮĩçĶ²
    0.35
    ORT
    0.32
    arra
    0.30
     oral
    0.27
    oral
    0.27
    -fire
    0.26
    OR
    0.26
     throat
    0.25
    çľĭå¾ħ
    0.25
    -na
    0.25
    Activations Density 0.019%

    No Known Activations