© 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. 36881
    Prev
    Next
    INDEX
    Explanations

    stories and tales

    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
     кÑĢÑĥп
    -0.09
    çī¹
    -0.08
    åĽ±
    -0.08
    åį¿
    -0.08
    æĹ©æĹ©
    -0.08
    prot
    -0.08
     crypt
    -0.08
    /icon
    -0.08
    åĪĨæķ£
    -0.07
     straw
    -0.07
    POSITIVE LOGITS
    Stories
    0.17
     stories
    0.17
     tales
    0.17
    轶
    0.17
    æķħäºĭ
    0.16
     Stories
    0.16
    ç»ıåİĨ
    0.15
    stories
    0.15
     tale
    0.15
    趣
    0.14
    Activations Density 0.109%

    No Known Activations