© 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. 8692
    Prev
    Next
    INDEX
    Explanations

    sailing and sailors

    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
    ional
    -0.12
     Äijỡ
    -0.10
    ions
    -0.10
    делÑĮ
    -0.09
    .Maybe
    -0.09
    ective
    -0.09
    æ¯ģ
    -0.09
    å¿¡
    -0.09
    halb
    -0.09
     continental
    -0.09
    POSITIVE LOGITS
    0.14
    wed
    0.09
    çĻĸ
    0.09
    th
    0.08
     Arabia
    0.08
    Grey
    0.08
    ģ
    0.08
    thers
    0.08
    ikk
    0.08
    ä¹ĭ家
    0.08
    Activations Density 0.010%

    No Known Activations