© 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. 22137
    Prev
    Next
    INDEX
    Explanations

    organizations

    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
    eri
    -0.09
    磼
    -0.09
    åĵī
    -0.09
    åѦçĶŁä»¬
    -0.08
    inar
    -0.08
    inars
    -0.08
    inos
    -0.08
    taÅŁ
    -0.08
    åĶĨ
    -0.07
    ãĤıãģĭ
    -0.07
    POSITIVE LOGITS
    åĴĮ个人
    0.14
    ummer
    0.10
    chie
    0.09
    ally
    0.09
    _JUMP
    0.09
    æ®Ĭ
    0.09
    orsch
    0.09
     piss
    0.09
    TRL
    0.09
    è¾ĸ
    0.09
    Activations Density 0.028%

    No Known Activations