© 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. 18652
    Prev
    Next
    INDEX
    Explanations

    former positions and titles

    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
    æѤæŶ
    -0.10
    æѤæĻĤ
    -0.10
    cano
    -0.10
    çĺ«
    -0.10
    ä¹ĭä¸ĭ
    -0.10
    å±ĬæŶ
    -0.10
    uelle
    -0.10
    ä¸Ģå¼Ģå§ĭå°±
    -0.09
    _ACL
    -0.09
    ungi
    -0.09
    POSITIVE LOGITS
    æľīè¿ĩ
    0.11
    为äºĨæĽ´å¥½
    0.09
    说è¿ĩ
    0.09
    森
    0.08
    (before
    0.08
    (now
    0.08
    arte
    0.08
     \@
    0.07
    éĤ£ç§į
    0.07
    çĹķ
    0.07
    Activations Density 0.097%

    No Known Activations