© 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. 14847
    Prev
    Next
    INDEX
    Explanations

    certain conditions or criteria

    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
    ç³»
    -0.19
    æĪĴ
    -0.19
    éĤ¦
    -0.19
    è¦ģç´§
    -0.19
    æ»ĭåij³
    -0.19
    .cb
    -0.19
    åij·
    -0.18
     anything
    -0.18
    è¿ijè§Ĩ
    -0.18
    æľ¬é¢Ĩ
    -0.18
    POSITIVE LOGITS
     certain
    0.21
    åĩłç§į
    0.21
    chor
    0.19
    çī¹å®ļ
    0.19
     Cummings
    0.19
    å¤ķ
    0.19
     namely
    0.18
     forfe
    0.18
    jan
    0.18
    导åIJij
    0.18
    Activations Density 0.349%

    No Known Activations