© 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. 35831
    Prev
    Next
    INDEX
    Explanations

    pairing or combinations

    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
    被æ·ĺæ±°
    -0.10
    Anchor
    -0.09
    iores
    -0.09
    cakes
    -0.08
    æĺ±
    -0.08
    ɯ
    -0.08
    igham
    -0.08
    urger
    -0.08
    æľªçŁ¥
    -0.08
    aru
    -0.08
    POSITIVE LOGITS
    æIJŃéħį
    0.31
     pairing
    0.22
    ç»ĦåIJĪ
    0.21
    éħį
    0.21
     combinations
    0.18
    æIJŃæ¡£
    0.18
     paired
    0.17
    éħįå¥Ĺ
    0.17
     ÑģоÑĩеÑĤ
    0.17
    éħįåIJĪ
    0.17
    Activations Density 0.192%

    No Known Activations