© 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. 54855
    Prev
    Next
    INDEX
    Explanations

    future actions or capabilities

    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
    æ¼ĵ
    -0.09
    è¶ħé«ĺ
    -0.09
    å¾Ģå¤ĸ
    -0.09
    éĢļæĬ¥
    -0.09
    aggi
    -0.09
    Dlg
    -0.09
    éĹ®çŃĶ
    -0.08
    æ¯ĶåĪ©æŶ
    -0.08
    åŀĵ
    -0.08
     kì
    -0.08
    POSITIVE LOGITS
    æIJŀå®ļ
    0.11
    塬
    0.09
    lsa
    0.09
    ä¹°åĪ°
    0.09
    ä»Ģä¹Īåij¢
    0.09
    æħİ
    0.09
    æį¢åıĸ
    0.09
    æ»ĭåħ»
    0.09
    äºĽä»Ģä¹Ī
    0.08
    å¹²ä»Ģä¹Ī
    0.08
    Activations Density 0.067%

    No Known Activations