© 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. 62362
    Prev
    Next
    INDEX
    Explanations

    collecting or collector

    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°²
    -0.10
    çĦ¦
    -0.09
    鼩
    -0.09
    éªĩ
    -0.09
    亮
    -0.09
    çĬĦ
    -0.09
     franch
    -0.08
    èĨ³
    -0.08
    åı¯çĶ¨
    -0.08
    讶
    -0.08
    POSITIVE LOGITS
    æĶ¶èĹı
    0.12
    沫
    0.10
    åİļåİļ
    0.10
     collector
    0.09
     pres
    0.09
     Collector
    0.09
     Slam
    0.09
    åĩłå¼ł
    0.08
     collectors
    0.08
    NH
    0.08
    Activations Density 0.130%

    No Known Activations