© 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. 22401
    Prev
    Next
    INDEX
    Explanations

    expectations or hopes

    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
    ä½ĵåĪ¶
    -0.09
    igs
    -0.09
    ald
    -0.09
     attractive
    -0.08
    ä¸įå®Į
    -0.08
     Lag
    -0.08
     Slate
    -0.07
    è½®æµģ
    -0.07
    ä¸įå®ļ
    -0.07
    å¿ĺè®°
    -0.07
    POSITIVE LOGITS
     expectations
    0.31
    æľŁæľĽ
    0.30
    æľŁå¾ħ
    0.27
     Expect
    0.26
     expectation
    0.25
    expect
    0.25
    Expect
    0.24
    EXPECT
    0.22
    _expect
    0.22
     expect
    0.21
    Activations Density 0.081%

    No Known Activations