© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36331
    Prev
    Next
    INDEX
    Explanations

    Red Sea, Arctic, Russo, Cross

    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
    èµĬ
    -0.10
    çł´
    -0.10
    åĩºåĽ½
    -0.09
    _VLAN
    -0.09
    çľ¼åīį
    -0.08
    æľ¬åĽ½
    -0.08
    éĽĴ
    -0.08
     foreign
    -0.08
    åĤ¬
    -0.08
    åıĮçľ¼
    -0.08
    POSITIVE LOGITS
    æĮĤåı·
    0.10
     Compass
    0.09
    æijģ
    0.09
     compass
    0.09
    å±±åİ¿
    0.08
    TintColor
    0.08
    æŃ¢
    0.08
    åѤçĭ¬
    0.08
    èĪŁå±±
    0.08
    èĩªæĿĢ
    0.08
    Activations Density 0.168%

    No Known Activations