© 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. 12431
    Prev
    Next
    INDEX
    Explanations

    festival

    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
    EMPL
    -0.20
    åįķä½į
    -0.20
    CHANT
    -0.20
    mort
    -0.20
     Redistributions
    -0.19
    让大家
    -0.19
     Newsp
    -0.19
    kdir
    -0.18
     revert
    -0.18
    vlan
    -0.18
    POSITIVE LOGITS
     Festival
    0.29
     festival
    0.28
     race
    0.24
    çĶµå½±èĬĤ
    0.22
     Race
    0.22
    race
    0.20
     Dialogue
    0.20
    çIJ¶
    0.20
    å¼Ģå¹ķå¼ı
    0.20
    ä»Ĭ
    0.20
    Activations Density 0.110%

    No Known Activations