© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12196
    Prev
    Next
    INDEX
    Explanations

    crystalline structures and crystallization

    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
    ðŁı»
    -0.20
    æī¬
    -0.19
    apist
    -0.18
    arty
    -0.18
    Jak
    -0.18
    /right
    -0.18
    èĩªè´Ł
    -0.18
    odzi
    -0.17
     Mud
    -0.17
    æ§Ń
    -0.17
    POSITIVE LOGITS
    ç»ĵæŀĦ
    0.24
     structure
    0.24
    çµIJæ§ĭ
    0.21
     structures
    0.20
    attice
    0.19
    æĢģ
    0.19
    .structure
    0.18
     fsm
    0.18
    纪å¾ĭ
    0.18
    ä¸ŃåĽ½æĶ¿åºľ
    0.18
    Activations Density 0.089%

    No Known Activations