© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36812
    Prev
    Next
    INDEX
    Explanations

    presale, presets, preserves

    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
    scar
    -0.10
    thon
    -0.09
    affer
    -0.09
    shal
    -0.09
    anness
    -0.09
    alem
    -0.08
    áĥ®
    -0.08
    ÑģÑħод
    -0.08
    纷纷
    -0.08
    swith
    -0.08
    POSITIVE LOGITS
    umably
    0.11
    bie
    0.11
    el
    0.10
    æł·åŃIJ
    0.10
    o
    0.10
    çĿĢä»ĸ
    0.09
    chool
    0.09
    ç³Ĭ
    0.09
    æŀ¶åŃIJ
    0.08
    pon
    0.08
    Activations Density 0.015%

    No Known Activations