© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20231
    Prev
    Next
    INDEX
    Explanations

    lot of

    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
    ASY
    -0.12
    åı£æ°Ķ
    -0.11
    spb
    -0.10
    asy
    -0.10
    ä¸Ģç»Ħ
    -0.09
    ASC
    -0.09
    oup
    -0.09
    çľĭå®Į
    -0.09
    èĩ¼
    -0.09
    éªĽ
    -0.09
    POSITIVE LOGITS
    ä¸įæĸŃåľ°
    0.10
    å½»
    0.09
     Chop
    0.09
    ä¸įåģľåľ°
    0.09
    itian
    0.09
    Glass
    0.09
    å®ŀå¹²
    0.09
    ä¸įæĸŃçļĦ
    0.09
    çĹĽ
    0.09
     use
    0.08
    Activations Density 0.034%

    No Known Activations