© 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. 27788
    Prev
    Next
    INDEX
    Explanations

    meeting

    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
    -0.10
    ebra
    -0.09
    å¨ģå°Ķ
    -0.09
    ngth
    -0.09
     brace
    -0.09
    enal
    -0.08
    åĥ»
    -0.08
    sq
    -0.08
    ç¾İåĮĸ
    -0.08
    ede
    -0.08
    POSITIVE LOGITS
    åĨįä¹Łä¸į
    0.10
    ioned
    0.09
    Occurred
    0.09
     Meeting
    0.09
    èĥ´
    0.09
    ä»Ķ
    0.09
    ropolis
    0.09
    èĤŁ
    0.09
    hips
    0.09
    ä¸ļåĨħ
    0.09
    Activations Density 0.023%

    No Known Activations