© 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. 21662
    Prev
    Next
    INDEX
    Explanations

    that followed by certain clauses

    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
    ä»Ģä¹Īåij¢
    -0.09
    çİ°å·²
    -0.09
    mates
    -0.09
    éĤ£å¤©
    -0.09
    èĢĮæĪIJ
    -0.09
    éĶ±
    -0.09
    cers
    -0.09
    å¤Ł
    -0.09
    .div
    -0.09
    ä¿İ
    -0.08
    POSITIVE LOGITS
    enties
    0.09
    strate
    0.09
    åĽłæѤ
    0.09
    _QUOTES
    0.08
    yor
    0.08
    hell
    0.08
     harbour
    0.08
    .googlecode
    0.08
    士
    0.08
    serter
    0.08
    Activations Density 0.065%

    No Known Activations