© 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. 50033
    Prev
    Next
    INDEX
    Explanations

    containing, contained, containment

    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
    หาร
    -0.10
     insight
    -0.09
    èķ¨
    -0.09
     ocup
    -0.09
     Occup
    -0.09
    Occup
    -0.09
     Rae
    -0.08
    eah
    -0.08
    éķIJ
    -0.08
    Offsets
    -0.08
    POSITIVE LOGITS
    ä½ıäºĨ
    0.13
     containment
    0.12
    ä¸įä½ı
    0.11
    ä¸į让
    0.11
    -contained
    0.10
    å¾Ĺä½ı
    0.10
    ä½ı
    0.10
    çĹħæĥħ
    0.10
    éģıåĪ¶
    0.10
    ä¸įè§ģ
    0.09
    Activations Density 0.043%

    No Known Activations