© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57314
    Prev
    Next
    INDEX
    Explanations

    golf course and club

    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
     ÑĦоÑĢ
    -0.10
    crew
    -0.09
    é¼»åŃIJ
    -0.09
     evils
    -0.09
    anst
    -0.08
    hood
    -0.08
    åĵ²
    -0.08
    ç¾İå¾·
    -0.08
    çŃĶåį·
    -0.08
    atural
    -0.08
    POSITIVE LOGITS
    æĸ§
    0.09
    tas
    0.08
    åĪĨæķ£
    0.08
    ÑĢай
    0.08
    رÙĬÙĤ
    0.08
    缸åħ³åĨħ容
    0.08
    èĩªèIJ¥
    0.08
    atts
    0.08
    æ±²åıĸ
    0.08
    หาร
    0.08
    Activations Density 0.005%

    No Known Activations