© 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. 39445
    Prev
    Next
    INDEX
    Explanations

    -ing verbs followed by a noun

    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
    sphere
    -0.10
    sweet
    -0.08
     standings
    -0.08
    rang
    -0.08
    sip
    -0.08
    åĪİ
    -0.07
    åıijå±ķä¸Ń
    -0.07
    hammer
    -0.07
    tti
    -0.07
    人éĻħ
    -0.07
    POSITIVE LOGITS
    soever
    0.11
    ä¸įä¸Ĭ
    0.11
    ande
    0.10
    å¦ĵ
    0.10
    FileVersion
    0.10
    Č↵
    0.10
    æ§İ
    0.09
    æľºåĪ¶
    0.09
    鼶ç¢İ
    0.09
    elsey
    0.09
    Activations Density 0.209%

    No Known Activations