© 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. 32489
    Prev
    Next
    INDEX
    Explanations

    jump and related motions

    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
    æ¼Ĥ
    -0.08
    à¸Ńà¸Ķ
    -0.08
    åħ¼
    -0.08
     RESP
    -0.08
    tl
    -0.08
    忸
    -0.08
    åĸĦæĦı
    -0.08
    棣
    -0.08
    hum
    -0.08
    mediately
    -0.07
    POSITIVE LOGITS
    æĹłæķ°æ¬¡
    0.09
    ä¸Ńéĵģ
    0.09
    综åIJĪæķ´æ²»
    0.09
    PIO
    0.09
    mere
    0.08
    arness
    0.08
    autop
    0.08
    assen
    0.08
    夷
    0.08
    undi
    0.08
    Activations Density 0.013%

    No Known Activations