© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16366
    Prev
    Next
    INDEX
    Explanations

    proper nouns from politics, tech, and entertainment

    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
    诬
    -0.22
    è·¤
    -0.19
    è¿ĩ硬
    -0.19
    夯å®ŀ
    -0.18
    伤害
    -0.18
    æī©æķ£
    -0.18
    è¶ģ
    -0.18
     affine
    -0.18
    è¯Ģ
    -0.17
    ÖĤ
    -0.17
    POSITIVE LOGITS
    å³Ĵ
    0.22
    ðŁı»
    0.20
    athi
    0.20
    0.19
    esda
    0.19
    åĴª
    0.19
    aign
    0.18
    绦
    0.18
    ])]
    0.18
    æªĢ
    0.18
    Activations Density 0.002%

    No Known Activations