© 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. 19106
    Prev
    Next
    INDEX
    Explanations

    pickup or variations of "up" as in "pick up steam"

    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
    аÑĢаÑĤ
    -0.09
     ÑħÑĢ
    -0.09
    æĺ¶
    -0.09
    åħħ
    -0.09
    isk
    -0.09
    iske
    -0.08
    _coll
    -0.08
    _outputs
    -0.08
    iska
    -0.08
    åĿ¨
    -0.08
    POSITIVE LOGITS
    åħ±é¸£
    0.10
    à¸Īาà¸ģà¸ģาร
    0.09
    åĭĩæ°Ķ
    0.09
    å¼Ģåħ³
    0.09
    undred
    0.08
    éģ½
    0.08
    èIJ¥åħ»
    0.08
    ä¹Łå¥½
    0.08
    çķĻåѦçĶŁ
    0.08
    çĤ¹æ»´
    0.08
    Activations Density 0.016%

    No Known Activations