© 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. 11399
    Prev
    Next
    INDEX
    Explanations

    marine life and species

    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
    _mono
    -0.20
    å®īåħ¨éļIJæĤ£
    -0.19
    çīį
    -0.19
    ues
    -0.18
    Scheme
    -0.18
    ive
    -0.18
    èļĬ
    -0.18
     stale
    -0.17
    ICS
    -0.17
    éĢ¸
    -0.17
    POSITIVE LOGITS
    æİĸ
    0.21
    å´´
    0.21
    ç¤ģ
    0.21
    letal
    0.21
    çŁ³æ²¹åĮĸå·¥
    0.21
    ç¬ı
    0.20
    _sku
    0.19
    /star
    0.19
    ABILITY
    0.18
    acific
    0.18
    Activations Density 0.006%

    No Known Activations