© 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. 13404
    Prev
    Next
    INDEX
    Explanations

    states of matter and transitions

    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
    íĹĢ
    -0.27
    âīĤ
    -0.23
    åģķ
    -0.23
    溯æºIJ
    -0.22
    _^(
    -0.22
    ä¸įåĪ°ä½į
    -0.21
    亲åĪĩ
    -0.21
     wÅĽ
    -0.20
    aunch
    -0.20
    sterol
    -0.20
    POSITIVE LOGITS
    液ä½ĵ
    0.28
     behavior
    0.26
    -fluid
    0.26
     properties
    0.26
    æĢģ
    0.26
     liquids
    0.26
    liquid
    0.26
    çī©è´¨
    0.25
    液
    0.25
     веÑīеÑģÑĤв
    0.24
    Activations Density 0.258%

    No Known Activations