© 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. 11716
    Prev
    Next
    INDEX
    Explanations

    calculi formation

    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
    é¦Ļæ°Ķ
    -0.20
    ÑĢеги
    -0.20
    wind
    -0.20
    åĬ²
    -0.19
    æ°Ķæģ¯
    -0.19
    contracts
    -0.18
    çī²
    -0.18
    èĤ¡æĿĥæĬķèµĦ
    -0.18
    å®ıè§Ĥ
    -0.18
    ouched
    -0.17
    POSITIVE LOGITS
    ç»ĵçŁ³
    0.31
     stones
    0.27
    ITES
    0.24
    ç¢İçīĩ
    0.23
    URN
    0.22
    çŁ³å¤´
    0.21
    å®ĿçŁ³
    0.21
    çĴ§
    0.20
    stones
    0.20
     stone
    0.20
    Activations Density 0.029%

    No Known Activations