© 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. 51218
    Prev
    Next
    INDEX
    Explanations

    his [relationship/place/role]

    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
    _FAST
    -0.09
    å¿ĥå¢ĥ
    -0.09
    èĶ
    -0.09
    åŃĺ
    -0.09
    è·¸
    -0.08
    irector
    -0.08
    rit
    -0.08
    ider
    -0.08
    çijĽ
    -0.08
    _hdr
    -0.08
    POSITIVE LOGITS
    æĶ¸
    0.10
    便ä¼ļ
    0.10
    porto
    0.09
    æ²IJæµ´
    0.09
    ULL
    0.08
    å°±å¤ŁäºĨ
    0.08
    CB
    0.08
    åīįæīĢ
    0.08
    å¥Ĺ
    0.08
     każ
    0.08
    Activations Density 0.335%

    No Known Activations