© 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. 52419
    Prev
    Next
    INDEX
    Explanations

    Schön, Meier, Schmeltzer, Schumacher, Schmeja, Schumay, Schilf, Schattdorf, Schauvliege, Schwenk

    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
    åħħæ²Ľ
    -0.13
    åĢ®
    -0.10
    icity
    -0.10
    å°ıé¢Ŀ
    -0.09
    ted
    -0.09
    تØŃ
    -0.09
    éķ¿è¾Ī
    -0.09
    ascal
    -0.09
    æľŁéĻIJ
    -0.09
    hta
    -0.09
    POSITIVE LOGITS
    neider
    0.10
    èĦĸåŃIJ
    0.10
    ultz
    0.09
    ramento
    0.09
    wright
    0.09
    yard
    0.09
    acter
    0.09
    å¯Įæ°ij
    0.09
    ops
    0.08
    åıijå±ķæ½ľåĬĽ
    0.08
    Activations Density 0.042%

    No Known Activations