© 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. 5363
    Prev
    Next
    INDEX
    Explanations

    fitting or matching

    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
    çĽĺ
    -0.10
    ç£IJ
    -0.09
    çī§
    -0.09
    éĺ¡
    -0.09
    acen
    -0.09
    æĥij
    -0.09
    å¾µ
    -0.09
    æĭīçĿĢ
    -0.09
    _RET
    -0.09
     sco
    -0.09
    POSITIVE LOGITS
     fit
    0.20
    Fit
    0.18
    fit
    0.17
     match
    0.17
    åĮ¹éħį
    0.17
     Fit
    0.16
    -fit
    0.16
     fits
    0.16
    _fit
    0.15
    match
    0.15
    Activations Density 0.049%

    No Known Activations