© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21820
    Prev
    Next
    INDEX
    Explanations

    wild 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
    åıī
    -0.10
    建çŃijæĿIJæĸĻ
    -0.09
    advance
    -0.09
    åĸĦ
    -0.09
    ateria
    -0.09
    ῦ
    -0.08
    对ä»ĺ
    -0.08
    .retry
    -0.08
    око
    -0.08
    hips
    -0.08
    POSITIVE LOGITS
    éĩİçĶŁ
    0.16
    éĩİå¤ĸ
    0.16
    éĩİ
    0.13
     wild
    0.13
    wild
    0.12
     Wild
    0.11
    Wild
    0.11
    çĶµç½ij
    0.10
    èĩªè¡Į
    0.10
    éĩİçĶŁåĬ¨çī©
    0.10
    Activations Density 0.089%

    No Known Activations