© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10090
    Prev
    Next
    INDEX
    Explanations

    shake like

    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
    ä¸Ģæīĭ
    -0.10
    ROT
    -0.10
    çĨı
    -0.09
    åįłåľ°
    -0.09
    ä¸ĢèĦļ
    -0.09
    éĢ¼
    -0.09
    ç¼°
    -0.09
    gom
    -0.09
     диÑĢ
    -0.09
    iker
    -0.09
    POSITIVE LOGITS
    æīĵæĸŃ
    0.09
    æħĪæĤ²
    0.09
    è¾Ĺ
    0.09
    èį£
    0.09
     Electric
    0.09
    ByUrl
    0.09
    éĢīæĭ
    0.08
    乡æĿij
    0.08
    æĤ´
    0.08
    esen
    0.08
    Activations Density 0.059%

    No Known Activations