© 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. 21251
    Prev
    Next
    INDEX
    Explanations

    preprint identifiers

    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
     Gentle
    -0.09
    ä¸ĭåįĬ
    -0.08
    æĸ°çĶŁ
    -0.08
    ifter
    -0.08
    åijĬ
    -0.07
     FB
    -0.07
    ç´ł
    -0.07
    ties
    -0.07
    ider
    -0.07
    uite
    -0.07
    POSITIVE LOGITS
    èģ
    0.11
    erson
    0.10
    èĬŁ
    0.10
     scient
    0.09
    _accepted
    0.09
    /job
    0.09
    åĪĨæµģ
    0.09
    elor
    0.08
    -anchor
    0.08
    æ»Ĥ
    0.08
    Activations Density 0.012%

    No Known Activations