© 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. 54453
    Prev
    Next
    INDEX
    Explanations

    operating systems or running software

    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
    èijŃ
    -0.11
    èĩ¼
    -0.10
    ban
    -0.10
    æĿµ
    -0.08
    ORAGE
    -0.08
    éħ°
    -0.08
    rift
    -0.08
     Bra
    -0.08
    éĶ®
    -0.08
    åıĥ
    -0.08
    POSITIVE LOGITS
    æĵįä½ľç³»ç»Ł
    0.11
    å¹³åı°ä¸Ĭ
    0.10
    ä»ĭè´¨
    0.10
    èĩªåıij
    0.10
    æĻļæľŁ
    0.09
    娱ä¹IJå¹³åı°
    0.09
     Linux
    0.09
    åĽ½åĬ¡éĻ¢
    0.09
    åIJİåı°
    0.08
    indows
    0.08
    Activations Density 0.244%

    No Known Activations