© 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. 12973
    Prev
    Next
    INDEX
    Explanations

    hurricanes and tropical storms

    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
    çĤĬ
    -0.22
    æ·¦
    -0.21
    çĶ°éĩİ
    -0.20
    ERTICAL
    -0.20
    çłį
    -0.19
    plemented
    -0.18
    pliers
    -0.18
    gger
    -0.18
    _ERRORS
    -0.17
    åįĪé¥Ń
    -0.17
    POSITIVE LOGITS
    带æĿ¥çļĦ
    0.22
    æ®ĩ
    0.21
    oS
    0.21
    aura
    0.20
    è·¨
    0.20
     Büyük
    0.19
     Newark
    0.19
    cco
    0.18
     lap
    0.18
    èĮĥ
    0.18
    Activations Density 0.006%

    No Known Activations