© 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. 14003
    Prev
    Next
    INDEX
    Explanations

    rupture

    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
    æijĩ头
    -0.22
    éĩįå¿ĥ
    -0.21
    踱
    -0.21
    å«ĸ
    -0.20
    loy
    -0.19
    رص
    -0.19
    èij±
    -0.19
    æŁĦ
    -0.18
    éĹªçĥģ
    -0.18
    注è§Ĩ
    -0.18
    POSITIVE LOGITS
    åºĦ
    0.20
    åIJİçļĦ
    0.19
    aneous
    0.19
     gamb
    0.19
    导èĩ´
    0.19
    acy
    0.18
    jah
    0.18
     PIT
    0.18
    agers
    0.18
    aca
    0.18
    Activations Density 0.084%

    No Known Activations