© 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. 18384
    Prev
    Next
    INDEX
    Explanations

    units of measurement or file sizes

    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
    å¾Ĥ
    -0.11
    沤
    -0.10
    ä¸Ģå¦Ĥ
    -0.09
    个å¤ļæľĪ
    -0.09
    个交æĺĵ
    -0.09
    ä¸Ģèµ·
    -0.09
    çļĦæ°Ķæģ¯
    -0.09
    viz
    -0.08
    åİĨ
    -0.08
    åĮ»æ²»
    -0.08
    POSITIVE LOGITS
     geg
    0.10
    ળ
    0.09
     lã
    0.09
    ltr
    0.09
    _histogram
    0.09
    ecom
    0.09
    olin
    0.09
    .readInt
    0.08
    appropri
    0.08
    _intr
    0.08
    Activations Density 0.291%

    No Known Activations