© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12444
    Prev
    Next
    INDEX
    Explanations

    claim, allegation, assertion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    èµ°å¾Ĺ
    -0.23
    åıijå±ķåīįæĻ¯
    -0.20
    æľºä¼ļ
    -0.19
    åıijå±ķæĪĺçķ¥
    -0.19
    åıijå±ķæľºéģĩ
    -0.19
    éĴī
    -0.18
    éĹ´éļĻ
    -0.18
     ÑĢолÑĮ
    -0.18
    åıijå±ķ空éĹ´
    -0.17
    æķ¬è¯·
    -0.17
    POSITIVE LOGITS
     claim
    0.29
     claims
    0.27
    claim
    0.26
     ÐIJлекÑģан
    0.24
    /assert
    0.24
     claimed
    0.21
     ÐĶм
    0.21
     ÐĶмиÑĤÑĢ
    0.21
     statement
    0.20
     statements
    0.20
    Activations Density 0.040%

    No Known Activations