© 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. 17014
    Prev
    Next
    INDEX
    Explanations

    units of length or mass

    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
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.10
    ãģĹãģ¾ãģĨ
    -0.10
    ä¸ºæľŁ
    -0.10
    од
    -0.10
    ows
    -0.09
    linger
    -0.09
    heet
    -0.09
    uzzi
    -0.09
    fried
    -0.09
    AVING
    -0.09
    POSITIVE LOGITS
    alog
    0.09
    ÑįÑĤомÑĥ
    0.09
    enticator
    0.08
    adays
    0.08
    вл
    0.08
     alternate
    0.08
    etheless
    0.08
    ä¸Ģ大æī¹
    0.08
    agement
    0.07
    oll
    0.07
    Activations Density 0.062%

    No Known Activations