© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37568
    Prev
    Next
    INDEX
    Explanations

    circus events

    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
    è´¢
    -0.10
    gett
    -0.08
    _MP
    -0.08
    itor
    -0.08
    oren
    -0.08
    aksi
    -0.08
    å·§åħĭåĬĽ
    -0.08
    Rated
    -0.08
    DataTable
    -0.08
    ieves
    -0.08
    POSITIVE LOGITS
    æīįåįİ
    0.10
    ä»°
    0.10
    çĶ¨åĵģ
    0.10
    çļĩåIJİ
    0.09
    éĺŁåijĺ
    0.09
    ï¸
    0.08
    èĪ¬çļĦ
    0.08
    èģĶåIJĪä¼ļ
    0.08
    ä¸ŀ
    0.08
    icana
    0.08
    Activations Density 0.006%

    No Known Activations