© 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. 10179
    Prev
    Next
    INDEX
    Explanations

    and or connecting lists

    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
    èIJĭ
    -0.10
    éľİ
    -0.09
    ottie
    -0.09
    ate
    -0.09
    è°Īèµ·
    -0.09
    å°±èĥ½å¤Ł
    -0.09
    æĸ°éĻĪ
    -0.09
    è¦ģ害
    -0.08
    èµ·ä¼ı
    -0.08
    è¿Ļæīį
    -0.08
    POSITIVE LOGITS
    adge
    0.10
    assin
    0.09
     Burton
    0.09
    oving
    0.08
     fon
    0.08
    ove
    0.08
    áŃ
    0.08
    جب
    0.08
    adius
    0.08
    -exclusive
    0.08
    Activations Density 0.171%

    No Known Activations