© 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. 48032
    Prev
    Next
    INDEX
    Explanations

    intermediate host

    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
    neau
    -0.10
    åŁİå¸Ĥ建设
    -0.09
    ä¸ī代
    -0.09
     pitches
    -0.09
    LAN
    -0.09
    stärke
    -0.09
     LAN
    -0.09
    estre
    -0.09
    _NC
    -0.08
     Watts
    -0.08
    POSITIVE LOGITS
    éĺ¶æ®µ
    0.11
    éĺ¶æ®µæĢ§
    0.10
    çķ¸å½¢
    0.09
    éļIJèĹı
    0.09
    åij½è¿IJ
    0.09
    å®
    0.09
     зак
    0.08
     stage
    0.08
    éıĸ
    0.08
    ego
    0.08
    Activations Density 0.125%

    No Known Activations