© 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. 10874
    Prev
    Next
    INDEX
    Explanations

    right choice or solution

    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
    ette
    -0.20
    itational
    -0.17
    hips
    -0.16
    yı
    -0.16
    aine
    -0.16
    emi
    -0.15
    -0.15
    ÑģÑĤÑĭ
    -0.15
    losure
    -0.15
    alty
    -0.15
    POSITIVE LOGITS
    zeitig
    0.29
    ness
    0.25
    eous
    0.24
    à¹Ĩ
    0.23
    iable
    0.22
    most
    0.22
    -sized
    0.21
    fully
    0.21
    ened
    0.20
    falls
    0.20
    Activations Density 0.111%

    No Known Activations