© 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. 12354
    Prev
    Next
    INDEX
    Explanations

    instrument or instrumentation

    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
    -0.20
    ëģĶ
    -0.18
    ened
    -0.17
    spots
    -0.16
    æĤłæĤł
    -0.16
    OrCreate
    -0.16
    à¹Ĩ
    -0.15
    ĵ
    -0.15
    çĺ©
    -0.15
    sense
    -0.15
    POSITIVE LOGITS
    ality
    0.23
    arium
    0.21
    eer
    0.21
    çļ¿
    0.20
    ally
    0.20
    ize
    0.20
    alist
    0.18
    ation
    0.18
    ations
    0.17
    esis
    0.17
    Activations Density 0.015%

    No Known Activations