© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21223
    Prev
    Next
    INDEX
    Explanations

    quality check or validation

    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
    èĥ½è¾¾åĪ°
    -0.11
    éļį
    -0.09
    gnu
    -0.09
    .setAuto
    -0.09
    crest
    -0.08
     Blow
    -0.08
    sett
    -0.08
    cope
    -0.08
    _closure
    -0.08
    eter
    -0.08
    POSITIVE LOGITS
    æł¸å®ŀ
    0.11
    æĺ¯åIJ¦æľī
    0.10
    åħ¥åı£
    0.09
     pháºŃn
    0.09
    åħ³èģĶ交æĺĵ
    0.09
    çŃĽéĢī
    0.09
    Incoming
    0.09
    åIJĪæ³ķæĢ§
    0.09
    imonial
    0.09
    åIJİåĨį
    0.09
    Activations Density 0.127%

    No Known Activations