© 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. 17225
    Prev
    Next
    INDEX
    Explanations

    use, modification and distribution

    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
    éķij
    -0.10
    capability
    -0.09
    ulet
    -0.09
    ä¸Ģå¿ĥ
    -0.09
    oser
    -0.09
     мало
    -0.08
     antis
    -0.08
    åıijå±ķåīįæĻ¯
    -0.08
    Capability
    -0.08
    åIJĿ
    -0.08
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.11
    âľĿ
    0.09
    åħ¶å®ĥ
    0.09
    iad
    0.09
    -fw
    0.09
    æĪijéĻ¢
    0.09
    æĸ°è¥¿
    0.08
     بذÙĦÙĥ
    0.08
    eron
    0.08
    Ñīен
    0.08
    Activations Density 0.074%

    No Known Activations