© 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. 51793
    Prev
    Next
    INDEX
    Explanations

    plant suffixes

    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
    åĸĦ
    -0.11
    éĢł
    -0.10
    大çģ«
    -0.09
    mdb
    -0.09
    éĿĵ
    -0.09
    èĸ®
    -0.09
    unn
    -0.09
    æĥij
    -0.08
    amo
    -0.08
     vir
    -0.08
    POSITIVE LOGITS
    ÑĤол
    0.10
    esse
    0.09
    èĤ±
    0.09
    race
    0.09
    å¤©åĽ½
    0.09
    åİ¿æĶ¿åºľ
    0.09
    _VOID
    0.08
     Taste
    0.08
    éĽªå±±
    0.08
    kur
    0.08
    Activations Density 0.004%

    No Known Activations