© 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. 15896
    Prev
    Next
    INDEX
    Explanations

    habitat modifications and losses

    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
    ingly
    -0.20
    estre
    -0.19
    ä»ħ代表
    -0.19
    tons
    -0.18
    æĢģ
    -0.17
    ë¥ł
    -0.16
    éĴ¢åİĤ
    -0.16
    å¿¡
    -0.16
    -ahead
    -0.16
    ses
    -0.16
    POSITIVE LOGITS
    ting
    0.23
    åĨħçļĦ
    0.19
    å¤ļæł·æĢ§
    0.19
    å¤ļä½į
    0.18
    广éĺĶ
    0.18
    iless
    0.18
    åĪ³
    0.18
    vez
    0.17
     areas
    0.17
    ë²
    0.17
    Activations Density 0.014%

    No Known Activations