© 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. 32097
    Prev
    Next
    INDEX
    Explanations

    former or old places/things

    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
    æĭ±
    -0.10
    æĿĸ
    -0.10
    å¸ĤåĮº
    -0.09
    羣çĪ±
    -0.09
    trail
    -0.09
    ardin
    -0.09
    è¿ĺç®Ĺ
    -0.09
    å°¾
    -0.09
    _FIFO
    -0.08
    ä½įæĸ¼
    -0.08
    POSITIVE LOGITS
    æĺĶæĹ¥
    0.12
    åİŁæĿ¥çļĦ
    0.11
    Former
    0.11
    åİŁæľīçļĦ
    0.10
    åºŁå¼ĥ
    0.10
    enthal
    0.10
    trs
    0.10
    åİŁæľī
    0.10
     abandoned
    0.10
    æŧ
    0.10
    Activations Density 0.090%

    No Known Activations