© 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. 49924
    Prev
    Next
    INDEX
    Explanations

    trainers, stable, people

    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
    æħ°
    -0.09
     Nested
    -0.08
    jets
    -0.08
     nested
    -0.08
    çĻ¾å§ĵ
    -0.08
    bol
    -0.08
    å¾ģæ±Ĥ
    -0.08
    Âł
    -0.08
    æľķ
    -0.08
    å®īæħ°
    -0.08
    POSITIVE LOGITS
    æīĺ
    0.09
    _RELEASE
    0.09
    åIJĦæĸ¹
    0.09
    èĢ³
    0.09
    TEAM
    0.09
    åĩºåĵģ
    0.08
    稳æŃ¥
    0.08
    åIJĪä¼Ļ人
    0.08
    åĽ¢éĺŁ
    0.08
    âĿĴ
    0.08
    Activations Density 0.004%

    No Known Activations