© 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. 12195
    Prev
    Next
    INDEX
    Explanations

    code constructs like var, if, bin

    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¸ij
    -0.20
    specifier
    -0.20
    ãģ£ãģįãĤĬ
    -0.20
    çĵł
    -0.19
    ä¸ĢåĢĭ人
    -0.19
    hlen
    -0.18
    åŃĹåı·
    -0.18
    æŶéĹ´æ®µ
    -0.18
    ppers
    -0.18
    ãģ«ãģªãĤĮ
    -0.18
    POSITIVE LOGITS
     cause
    0.19
     men
    0.19
     concern
    0.19
    çŃīå·¥ä½ľ
    0.19
     op
    0.18
     eyes
    0.18
     web
    0.18
     work
    0.18
     defense
    0.18
     fear
    0.18
    Activations Density 0.001%

    No Known Activations