© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8913
    Prev
    Next
    INDEX
    Explanations

    pool

    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
    ry
    -0.12
    itious
    -0.10
    åĪ©äºļ
    -0.09
    oring
    -0.09
    èĥ¡åŃIJ
    -0.08
    æį§
    -0.08
    ç¿¥
    -0.08
    ãģıãĤĮ
    -0.08
    emas
    -0.08
    ulous
    -0.08
    POSITIVE LOGITS
    mates
    0.12
    å¡ĺ
    0.12
    åĵĩ
    0.12
    side
    0.11
    人士
    0.10
     ë¶Ī구íķĺê³ł
    0.10
    idon
    0.10
    inator
    0.10
    BIND
    0.10
    ULAR
    0.10
    Activations Density 0.014%

    No Known Activations