© 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. 19883
    Prev
    Next
    INDEX
    Explanations

    time travel and future events

    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
    pite
    -0.11
    _modules
    -0.09
    åŃĶ
    -0.09
    æģ¯
    -0.09
    åĵī
    -0.09
    俸
    -0.09
    å¼ĢéŨ
    -0.09
    .sat
    -0.09
    ä¸įéĻIJ
    -0.09
    ä¸ij
    -0.08
    POSITIVE LOGITS
    年代
    0.11
    ords
    0.10
    交éĢļ
    0.10
    åĿŀ
    0.09
    åĬ«
    0.09
    åĽłæŀľ
    0.09
    éĺ»
    0.09
    交éĢļå®īåħ¨
    0.08
    æł¸å®ļ
    0.08
    é³ĸ
    0.08
    Activations Density 0.113%

    No Known Activations