© 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. 19036
    Prev
    Next
    INDEX
    Explanations

    data analysis and insights

    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
    ÐĺÐĿ
    -0.09
    çķ¿
    -0.08
    罨
    -0.08
    è§ĦèĮĥåĮĸ
    -0.08
    èĩ´
    -0.08
    OnInit
    -0.08
    çŃ¹éĽĨ
    -0.08
    èĢħçļĦ
    -0.08
    OrFail
    -0.08
    å°ģè£ħ
    -0.08
    POSITIVE LOGITS
    åIJİåı°
    0.12
    åıįé¦Ī
    0.12
    æķ°æį®åĪĨæŀIJ
    0.12
    åĪĨæŀIJ
    0.12
    ç»Łè®¡
    0.12
    çļĦè¶ĭåĬ¿
    0.10
    åĽŀé¦Ī
    0.10
    ç»Łè®¡æķ°æį®
    0.10
     feedback
    0.10
    è¶ĭåĬ¿
    0.10
    Activations Density 0.120%

    No Known Activations