© 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. 35647
    Prev
    Next
    INDEX
    Explanations

    recovery and stimulus packages

    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
    çĥŃ带
    -0.10
    è±Ĩ
    -0.08
    onen
    -0.08
    ôn
    -0.08
    æµģæĺŁ
    -0.08
    éĵİ
    -0.08
    è¢ĭ
    -0.08
    åī¯ä¼ļéķ¿
    -0.08
     bread
    -0.08
    æķĻä¼ļ
    -0.08
    POSITIVE LOGITS
    éĵ¸
    0.10
    aland
    0.10
    è§īå¾Ĺå¾Ī
    0.09
    纡
    0.09
     Trout
    0.09
    绳
    0.09
    鸳
    0.09
    æ»ŀ
    0.09
    orre
    0.09
    SCRI
    0.09
    Activations Density 0.055%

    No Known Activations