© 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. 8356
    Prev
    Next
    INDEX
    Explanations

    remote desktop, terminal, shortcuts

    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
    éĤĥ
    -0.10
    æ°¸
    -0.09
    çļĦæľĭåıĭ
    -0.09
    åįĹåĮĹ
    -0.09
    æł¹æį®èĩªå·±
    -0.09
    ä¹Łéļıä¹ĭ
    -0.09
    ä¿Ŀè´¹
    -0.09
    廪
    -0.08
     Ginger
    -0.08
    åıĪæľī
    -0.08
    POSITIVE LOGITS
    æĥ¦
    0.09
    _terminal
    0.09
    åĬŁå¤«
    0.09
    èĵ®
    0.09
    éľ²
    0.09
     shells
    0.08
    æ¡Ķ
    0.08
    èݲ
    0.08
    urse
    0.08
    æ¡Į
    0.08
    Activations Density 0.160%

    No Known Activations