© 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. 12240
    Prev
    Next
    INDEX
    Explanations

    family members and names

    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
    lander
    -0.20
    ì²´
    -0.20
    robe
    -0.19
    à¹Į
    -0.18
    éļĻ
    -0.18
    æ®Ĩ
    -0.18
    rosse
    -0.17
    owy
    -0.17
    èĦĸ
    -0.17
    immer
    -0.17
    POSITIVE LOGITS
    们çļĦ
    0.26
    们
    0.23
    ðŁı»
    0.20
    åĢij
    0.20
    å¨ĺ
    0.18
    defaultValue
    0.17
    们éĥ½
    0.17
    lic
    0.17
    è¦ģçŁ¥éģĵ
    0.17
    doll
    0.16
    Activations Density 0.029%

    No Known Activations