© 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. 37043
    Prev
    Next
    INDEX
    Explanations

    tone and voice description

    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
    æĺ¯æľĢ好çļĦ
    -0.09
    iT
    -0.08
    åŀĤ
    -0.08
     ign
    -0.08
    è¡Į人
    -0.08
    _primitive
    -0.08
     coup
    -0.08
     WWW
    -0.08
    visibility
    -0.07
    blo
    -0.07
    POSITIVE LOGITS
    è¯Ńæ°Ķ
    0.22
     tone
    0.16
    é£İæł¼
    0.15
    åŁºè°ĥ
    0.15
    æݪ
    0.14
    åı£æ°Ķ
    0.14
    tone
    0.13
     Tone
    0.13
    æĢģ度
    0.12
    æĦıåĽ¾
    0.12
    Activations Density 0.073%

    No Known Activations