© 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. 4978
    Prev
    Next
    INDEX
    Explanations

    vestibular system and balance

    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
    loh
    -0.11
    åħ³æĢĢ
    -0.10
    çĿ¹
    -0.09
    檩
    -0.09
    SAMPLE
    -0.09
    åİĭæĬij
    -0.09
    .EntityManager
    -0.08
    æĭīå¼Ģ
    -0.08
    обÑī
    -0.08
    <Edge
    -0.08
    POSITIVE LOGITS
    éĻĢ
    0.12
    导èĪª
    0.10
    ermen
    0.09
    GPS
    0.09
     GPS
    0.09
    å¤Ķ
    0.09
    èĪªæµ·
    0.09
    æ¯Ľ
    0.09
     gps
    0.09
    笼
    0.09
    Activations Density 0.142%

    No Known Activations