© 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. 32842
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    çĬ¯
    -0.09
    mono
    -0.09
    mf
    -0.08
    æĮģæľīçļĦ
    -0.08
    ReturnValue
    -0.08
    åĪ°åºķ
    -0.08
    uels
    -0.08
    derived
    -0.08
    IVA
    -0.08
    _renderer
    -0.08
    POSITIVE LOGITS
    æľīåħ³éĥ¨éŨ
    0.10
    丢äºĨ
    0.09
    椿
    0.09
    æ³¼
    0.08
    åĤ¢
    0.08
    èĵ¬åĭĥ
    0.08
    im
    0.08
    å¸ĥæĭī
    0.08
    rap
    0.08
     Fee
    0.08
    Activations Density 0.017%

    No Known Activations