© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7334
    Prev
    Next
    INDEX
    Explanations

    its uniqueness

    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
    dana
    -0.13
    ingly
    -0.11
    æĪij没
    -0.10
    è´¢
    -0.10
     конеÑĩно
    -0.09
    å±ĬæŶ
    -0.09
    inet
    -0.09
    üc
    -0.09
    æĪijè¿ĺ
    -0.09
    æĤ¨å¥½
    -0.08
    POSITIVE LOGITS
    æ¶Ī
    0.08
     own
    0.08
    Spatial
    0.08
    è±ģ
    0.08
    untu
    0.08
    è¯Ŀ说
    0.08
    è·»
    0.07
    æī¼
    0.07
    bull
    0.07
     Bil
    0.07
    Activations Density 0.120%

    No Known Activations