© 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. 6587
    Prev
    Next
    INDEX
    Explanations

    search queries and results

    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
    ä¸Ģ对ä¸Ģ
    -0.09
    é«ĺå³°
    -0.09
    	TokenName
    -0.09
    以èī²
    -0.08
    fone
    -0.08
    _PARAMETERS
    -0.08
     Turing
    -0.08
    è±¹
    -0.08
    orest
    -0.08
    nyder
    -0.08
    POSITIVE LOGITS
    ä¸įçŁ¥ä¸įè§ī
    0.10
    ложений
    0.09
    符åIJĪæĿ¡ä»¶
    0.08
    è¿ijçĻ¾
    0.08
     Sort
    0.08
     sorted
    0.08
    Substring
    0.08
    Sort
    0.08
    è°
    0.08
    ä¿¡æīĺ
    0.08
    Activations Density 0.016%

    No Known Activations