© 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. 29826
    Prev
    Next
    INDEX
    Explanations

    buildings and centers

    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
    _chg
    -0.10
    æĶ¶åī²
    -0.08
    洪水
    -0.08
    ByPrimaryKey
    -0.08
    ä¹ĹãĤĬ
    -0.08
    rant
    -0.08
    管å±Ģ
    -0.08
    Ñĥл
    -0.08
    egen
    -0.08
    Ñĩен
    -0.08
    POSITIVE LOGITS
    è½»
    0.09
    çĪ¶åŃIJ
    0.09
    åIJ¬è¯´
    0.09
     Lair
    0.09
    æĬ±
    0.09
    alsa
    0.09
    æīĩ
    0.08
    樱
    0.08
    éĽĨåĽ¢èĤ¡ä»½
    0.08
    EEP
    0.08
    Activations Density 0.069%

    No Known Activations