© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54059
    Prev
    Next
    INDEX
    Explanations

    cranial nerves or ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç²Ĵ
    -0.10
    ä¿®åħ»
    -0.09
    å°º
    -0.09
    selectors
    -0.08
    .Bad
    -0.08
    ä¸¥æł¼çļĦ
    -0.08
    è¿Ŀæ³ķ
    -0.08
    .level
    -0.08
    ALS
    -0.08
     geld
    -0.08
    POSITIVE LOGITS
    èļ©
    0.09
    æĥ³ä¸įåĪ°
    0.09
    æ±´
    0.08
    éĻĽ
    0.08
    oron
    0.08
    çĶij
    0.08
    åİŁæĿ¥
    0.08
    ocked
    0.08
    lit
    0.08
     McGr
    0.08
    Activations Density 0.251%

    No Known Activations