© 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. 12843
    Prev
    Next
    INDEX
    Explanations

    plant species and flora

    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
    å®Ļ
    -0.18
     Mines
    -0.18
    oodle
    -0.18
    çŁ¿åĮº
    -0.17
    渤海
    -0.17
     Äijảo
    -0.17
    åŃĶ
    -0.17
    æµģåĬ¨æĢ§
    -0.17
    鼬
    -0.17
    _allocator
    -0.17
    POSITIVE LOGITS
    åħĢ
    0.20
    forms
    0.20
     grown
    0.19
    çĶŁéķ¿
    0.19
     RESP
    0.18
    ä¸Ńè¶ħ
    0.18
    éļľ
    0.17
    _SR
    0.17
    ç§įç±»
    0.17
    为主ä½ĵ
    0.17
    Activations Density 0.057%

    No Known Activations