© 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. 8080
    Prev
    Next
    INDEX
    Explanations

    Oliver followed by names

    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
    ãģĺ
    -0.11
    stä
    -0.09
    ingly
    -0.09
    alog
    -0.09
    ÑĮÑİ
    -0.09
    loe
    -0.09
    ORIZED
    -0.09
    ipt
    -0.08
    itivity
    -0.08
    elijk
    -0.08
    POSITIVE LOGITS
    -minded
    0.14
     minded
    0.12
    ance
    0.12
    ware
    0.11
    ìį¨
    0.11
    andra
    0.09
    roman
    0.09
    estre
    0.09
    raries
    0.09
    åħ¶ä¸Ńä¸Ģ个
    0.09
    Activations Density 0.015%

    No Known Activations