© 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. 55757
    Prev
    Next
    INDEX
    Explanations

    parts of plants and animals

    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
    çŃIJ
    -0.09
    .mk
    -0.09
    è½°
    -0.09
    壮è§Ĥ
    -0.08
    çĶŁåĬ¨
    -0.08
    èĶļ
    -0.08
     ctor
    -0.08
    èĬĴ
    -0.08
    rze
    -0.08
    .go
    -0.08
    POSITIVE LOGITS
    inous
    0.10
    衬
    0.10
    æĴĴ
    0.09
    æ±ŁåįĹ
    0.09
    主æĦı
    0.08
    CHE
    0.08
    lte
    0.08
    itty
    0.08
    éij
    0.08
    lin
    0.08
    Activations Density 0.035%

    No Known Activations