© 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. 5807
    Prev
    Next
    INDEX
    Explanations

    skull and brain anatomy

    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
     обоÑĢ
    -0.10
    åħį责声æĺİ
    -0.10
    åĽ¢
    -0.10
    åĵij
    -0.10
    å¦Ĥå®ŀ
    -0.09
    åı¯è§Ĥ
    -0.09
    å¤ĦåĪĨ
    -0.09
    æĬĺåıł
    -0.09
    æµ·æ£ł
    -0.09
    _machine
    -0.09
    POSITIVE LOGITS
    头顶
    0.10
    çĿ¿
    0.10
    头çĹĽ
    0.09
    é¢ħ
    0.09
    èĦij
    0.09
    è¯Ī
    0.09
    åĽŁ
    0.09
     skull
    0.09
     cere
    0.09
    èħ¦
    0.08
    Activations Density 0.246%

    No Known Activations