© 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. 16657
    Prev
    Next
    INDEX
    Explanations

    recording media and apparatuses

    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»
    -0.24
    -0.23
    enger
    -0.19
    reen
    -0.18
    ently
    -0.18
    ðŁı¼
    -0.17
    ided
    -0.17
    eners
    -0.17
    endra
    -0.16
    lander
    -0.16
    POSITIVE LOGITS
    OrUpdate
    0.20
    ives
    0.19
    /display
    0.17
    -breaking
    0.17
     noqa
    0.17
    INAL
    0.17
    SSION
    0.16
    ãģĭãģ¤
    0.16
    ENTER
    0.16
    FFE
    0.16
    Activations Density 0.052%

    No Known Activations