© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 17294
    Prev
    Next
    INDEX
    Explanations

    ’cause, ’90s, ’70s, ’80s, ’50s, ’17, ’20, ’73

    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
    ../../../
    -0.16
    ëģĶ
    -0.13
     ìķĦëĭĪëĿ¼
    -0.12
    ãģĦãģĨ
    -0.11
    Ùĭ
    -0.10
    ings
    -0.10
    åģ¾
    -0.09
    ação
    -0.09
    ilon
    -0.09
    ä¸ĩåįļ
    -0.09
    POSITIVE LOGITS
    ernal
    0.11
     ë¶Ī구íķĺê³ł
    0.11
    gether
    0.10
    istic
    0.10
    unes
    0.10
    èĩ¾
    0.10
    andom
    0.10
    egration
    0.10
    ial
    0.10
    ê¹IJ
    0.10
    Activations Density 0.010%

    No Known Activations