© 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. 37771
    Prev
    Next
    INDEX
    Explanations

    aircraft, wings, tail, wheels

    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
    å®ļåIJij
    -0.10
    ä¾¿å®ľ
    -0.09
    éĻ¡
    -0.09
    èµ·èįī
    -0.09
    çĥ¦æģ¼
    -0.09
    åįķ项
    -0.08
    _PROVID
    -0.08
    çıł
    -0.08
     vere
    -0.08
     Eisen
    -0.08
    POSITIVE LOGITS
    íĪ¬
    0.09
    èĢģé¾Ħ
    0.09
    èĶ¬
    0.09
    holm
    0.08
    ç¿İ
    0.08
    èıħ
    0.08
    è¯ij
    0.08
    £¼
    0.08
    åłĥ
    0.08
    .SDK
    0.08
    Activations Density 0.094%

    No Known Activations