© 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. 35890
    Prev
    Next
    INDEX
    Explanations

    characteristics and properties

    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
    ç»Ĩç»Ĩ
    -0.09
     деле
    -0.09
    èį«
    -0.08
     дело
    -0.08
    ares
    -0.08
    lac
    -0.08
    æįĭ
    -0.08
    éĺħ
    -0.08
    ãģ°
    -0.08
    pd
    -0.08
    POSITIVE LOGITS
     specifications
    0.13
    æĢ§èĥ½
    0.12
     specs
    0.12
    çī¹çĤ¹
    0.12
     characteristics
    0.11
    æºŁ
    0.11
     properties
    0.10
    èĪĴéĢĤ
    0.10
     profile
    0.10
    è½®å»ĵ
    0.10
    Activations Density 0.154%

    No Known Activations