© 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. 37328
    Prev
    Next
    INDEX
    Explanations

    PRNewswire, SBWIRE, CCNMatthews

    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
    uzzy
    -0.10
    çĩł
    -0.10
    çįIJ
    -0.09
    åĪ¸
    -0.09
    碧æ¡ĤåĽŃ
    -0.09
    äºĶåįĥ
    -0.09
    èħ»
    -0.09
    èĦĨå¼±
    -0.09
    @email
    -0.09
    æĪĸå°Ĩ
    -0.08
    POSITIVE LOGITS
    AGMA
    0.08
    éĶ¦
    0.08
    AGIC
    0.08
    çIJ´
    0.08
    /release
    0.08
    åĬĽéĩı
    0.08
    loon
    0.07
    ä¸įå¾Ĺå·²
    0.07
    posta
    0.07
    p
    0.07
    Activations Density 0.031%

    No Known Activations