© 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. 32230
    Prev
    Next
    INDEX
    Explanations

    Bitcoin mining

    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
    妥
    -0.09
    æīĢè¬Ĥ
    -0.08
    å°±æĪIJäºĨ
    -0.08
    å°±è¦ģ
    -0.08
    æĪij们就
    -0.08
    æĭ¿èµ·
    -0.08
    å°±å¾Ī
    -0.08
    åıĪèĥ½
    -0.08
     logo
    -0.08
    çIJ¢ç£¨
    -0.08
    POSITIVE LOGITS
    æľī两ç§į
    0.10
    oused
    0.10
    Manifest
    0.09
    _chance
    0.09
    çĭIJ
    0.09
     ActionBar
    0.08
    çĶŁçIJĨ
    0.08
    使çĶ¨èĢħ
    0.08
    _manifest
    0.08
    æľīä¸Ģå®ļ
    0.08
    Activations Density 0.085%

    No Known Activations