© 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. 7150
    Prev
    Next
    INDEX
    Explanations

    bite or biting

    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
    stration
    -0.11
     воÑĤ
    -0.09
    erate
    -0.09
    å§Ķ书记
    -0.09
    alendar
    -0.09
    ợ
    -0.08
    ence
    -0.08
    forth
    -0.08
    ists
    -0.08
    nt
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģåı£
    0.11
    tur
    0.11
    ted
    0.11
    iful
    0.10
     Bite
    0.10
    ting
    0.10
    鸥
    0.10
    utor
    0.10
    bite
    0.10
    ÅŁe
    0.10
    Activations Density 0.011%

    No Known Activations