© 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. 1175
    Prev
    Next
    INDEX
    Explanations

    made his

    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
     Dead
    -0.09
    åĵĦ
    -0.09
     Crack
    -0.08
    нал
    -0.08
    å¥ĩæĢª
    -0.08
    å°Ħ
    -0.08
    tool
    -0.08
    éĤ®æĶ¿
    -0.08
    ç®ĢåİĨ
    -0.08
     Nag
    -0.07
    POSITIVE LOGITS
    æijĬ
    0.11
    æĿĤçī©
    0.10
    _tac
    0.10
    HOLDER
    0.09
    æ§Ľ
    0.09
    uciones
    0.09
    åĮĹç¾İ
    0.09
    ä¼°
    0.09
    æŀ¶
    0.09
    åij¨ä¸ī
    0.09
    Activations Density 0.036%

    No Known Activations