© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7984
    Prev
    Next
    INDEX
    Explanations

    asking a question

    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
    etas
    -0.11
    ç©·
    -0.10
    çĽ¼
    -0.09
     Rudd
    -0.09
    findViewById
    -0.09
    æŦ
    -0.09
    ished
    -0.09
    /dir
    -0.08
    akis
    -0.08
    eryl
    -0.08
    POSITIVE LOGITS
    ä¸İæѤ
    0.10
    ori
    0.09
    æĿľåħ°
    0.08
    æ§į
    0.08
    lay
    0.08
    仪
    0.08
    è¥Ħéĺ³
    0.08
    landers
    0.08
    æ°Ķæ°Ľ
    0.07
    oplast
    0.07
    Activations Density 2.640%

    No Known Activations