© 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. 36212
    Prev
    Next
    INDEX
    Explanations

    alphabetical listing and sorting

    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
    å¤ļå¤ļ
    -0.10
    æĻ¯å¾·
    -0.09
    obo
    -0.09
    _markers
    -0.08
    iden
    -0.08
    ouston
    -0.08
    åĢĴåħ¥
    -0.08
    帮åĬ©ä¼ģä¸ļ
    -0.08
     thÆ°á»Ľc
    -0.08
    udson
    -0.08
    POSITIVE LOGITS
     alphabet
    0.15
     Alphabet
    0.13
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.13
    alphabet
    0.13
     alphabetical
    0.13
    phabet
    0.12
    åŃĹæ¯į
    0.11
    abcdefghijklmnopqrstuvwxyz
    0.09
     alph
    0.09
    ABCDE
    0.09
    Activations Density 0.103%

    No Known Activations