© 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. 3873
    Prev
    Next
    INDEX
    Explanations

    like saying, like how, like a

    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
    符
    -0.11
    符åı·
    -0.10
    å°ı康
    -0.09
    åľĺ
    -0.09
    å¥Ĺè£ħ
    -0.09
    è£ħåį¸
    -0.09
    æ°ijæĶ¿å±Ģ
    -0.09
    нÑĥÑĤ
    -0.09
    没人
    -0.08
    èĪħèĪħ
    -0.08
    POSITIVE LOGITS
    å°±å¦ĤåIJĮ
    0.09
    å°±åĥı
    0.09
    aho
    0.09
    çŀ½
    0.08
     Credits
    0.08
    çĽ²
    0.08
     blind
    0.08
    ä»Ģä¹Īåij¢
    0.08
    Credits
    0.08
    ä¸Ģå¼Ģå§ĭå°±
    0.08
    Activations Density 0.034%

    No Known Activations