© 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. 20780
    Prev
    Next
    INDEX
    Explanations

    asteroid belt

    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
    éĩįæĸ°
    -0.10
    loh
    -0.10
    kest
    -0.10
    AAF
    -0.10
    istrar
    -0.10
     Cly
    -0.09
     thuyết
    -0.09
    ÑĦÑĢ
    -0.09
    vi
    -0.09
    führ
    -0.09
    POSITIVE LOGITS
     belt
    0.10
    uml
    0.08
    belt
    0.08
    ä¸ĩè¾Ĩ
    0.08
    targets
    0.08
    èĶ¬èıľ
    0.08
    åį±
    0.08
    çĶŁçĶŁ
    0.08
    èµĽè½¦
    0.08
     Belt
    0.08
    Activations Density 0.018%

    No Known Activations