© 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. 55453
    Prev
    Next
    INDEX
    Explanations

    required or needed

    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
     ever
    -0.09
    æľ¬èº«å°±
    -0.09
    å§ĭç»Īä¿ĿæĮģ
    -0.09
    è¾¾åĪ°äºĨ
    -0.09
    建ç«ĭäºĨ
    -0.08
    ever
    -0.08
    大大å°ı
    -0.08
     Bron
    -0.08
     EVER
    -0.08
    以åħ¶
    -0.08
    POSITIVE LOGITS
     ÑĤÑĢебÑĥеÑĤÑģÑı
    0.16
     íķĦìļĶ
    0.16
    ãģĮå¿ħè¦ģ
    0.15
     needed
    0.14
     Needed
    0.14
    å¿ħè¦ģçļĦ
    0.13
    æīįèĥ½
    0.13
    needed
    0.13
    required
    0.13
     required
    0.13
    Activations Density 0.197%

    No Known Activations