© 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. 15338
    Prev
    Next
    INDEX
    Explanations

    exclude or rule out possibility

    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
    ICES
    -0.17
     поÑĢÑıд
    -0.17
    arness
    -0.17
     ÑĢазв
    -0.17
    ä¸Ī
    -0.16
    RAIN
    -0.16
    riangle
    -0.16
    angered
    -0.16
    Ñĩик
    -0.16
    tries
    -0.15
    POSITIVE LOGITS
     possibility
    0.30
    æİī
    0.26
     возможноÑģÑĤÑĮ
    0.26
     possibilité
    0.25
    å¤į
    0.24
    oute
    0.24
    æİīäºĨ
    0.23
     Möglichkeit
    0.22
     possibilities
    0.22
     possibilitÃł
    0.22
    Activations Density 0.016%

    No Known Activations