© 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. 13130
    Prev
    Next
    INDEX
    Explanations

    tyres and tires

    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
    ILED
    -0.25
    nia
    -0.22
    undy
    -0.21
    㶲
    -0.20
    jej
    -0.20
    æ¡Ĩ
    -0.20
     Platt
    -0.19
     Inhal
    -0.19
     uLocal
    -0.19
    èĮ¬
    -0.19
    POSITIVE LOGITS
    è½®èĥİ
    0.35
     tyres
    0.32
    æ©¡èĥ¶
    0.29
     tyre
    0.27
     tires
    0.27
    æ²¥éĿĴ
    0.27
    è·¯éĿ¢
    0.26
    è¡Į车
    0.25
    è¡Į驶
    0.24
    磨æįŁ
    0.24
    Activations Density 0.041%

    No Known Activations