© 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. 35756
    Prev
    Next
    INDEX
    Explanations

    recent events and news

    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
    æĸ°æĹ¶æľŁ
    -0.12
    æѤåīį
    -0.11
    çŃīçĿĢ
    -0.10
    æľªæĿ¥åıijå±ķ
    -0.10
    å°Ĭéĩį
    -0.10
    æĹ¥åIJİ
    -0.10
     eventually
    -0.10
     eventual
    -0.10
    å½ĵåĪĿ
    -0.10
    å¦Ĥä»Ĭ
    -0.09
    POSITIVE LOGITS
    emente
    0.15
    /current
    0.11
    ulus
    0.11
    izedName
    0.10
    mente
    0.10
     grads
    0.10
    imes
    0.10
    isers
    0.09
    abouts
    0.09
    icot
    0.09
    Activations Density 0.039%

    No Known Activations