© 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. 38681
    Prev
    Next
    INDEX
    Explanations

    Bipolar transistor

    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
    çĻ»
    -0.10
    åĩºæīĭ
    -0.09
    ABEL
    -0.09
    ãĤĨ
    -0.09
    è¾ĭ
    -0.09
    аниÑĨ
    -0.09
     peÅĤ
    -0.09
    èįī
    -0.08
    溪
    -0.08
    ç¾ģ
    -0.08
    POSITIVE LOGITS
    å¹ķ
    0.09
     gain
    0.09
    奸
    0.08
    æķĻèĤ²èµĦæºIJ
    0.08
    ç³ł
    0.08
    导游
    0.08
    æĶ¾å¤§
    0.08
     Gain
    0.08
    解æĶ¾
    0.08
    éĻµ
    0.08
    Activations Density 0.064%

    No Known Activations