© 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. 38230
    Prev
    Next
    INDEX
    Explanations

    names

    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
    -0.10
    orns
    -0.08
     Harding
    -0.08
    AREN
    -0.08
    åĤį
    -0.08
    è¿Ń
    -0.08
     Nuggets
    -0.07
    nev
    -0.07
    ombs
    -0.07
     lag
    -0.07
    POSITIVE LOGITS
    ä¿£
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.10
    ette
    0.10
    æłĭ
    0.10
    æĬĢå¸Ī
    0.10
    éĹ®éĹ®
    0.09
    请çĤ¹åĩ»
    0.09
    æĺĨä»ij
    0.09
    åģ¥
    0.09
    AGMA
    0.09
    Activations Density 0.657%

    No Known Activations