© 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. 8762
    Prev
    Next
    INDEX
    Explanations

    highs and lows

    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
    iken
    -0.10
    Ñĩин
    -0.10
    è¾ķ
    -0.09
    ÑĩÑĮ
    -0.09
    èĥŃ
    -0.09
    ç®Ģæĺĵ
    -0.09
    èĩ³ä¸Ĭ
    -0.09
    æĭĩæĮĩ
    -0.08
    çļĸ
    -0.08
    çŀ¬
    -0.08
    POSITIVE LOGITS
    ä¸Ģæī¹
    0.09
    åĸĬ
    0.09
    NavigationBar
    0.09
    å¨ģæħij
    0.09
    æ¡ĥ
    0.08
    éŃģ
    0.08
    obuf
    0.08
    ìłIJìĿĦ
    0.08
    ibase
    0.08
    acey
    0.08
    Activations Density 0.022%

    No Known Activations