© 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. 16663
    Prev
    Next
    INDEX
    Explanations

    What happens when/if

    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
    çIJĨçĶ±
    -0.19
    èĤ²äºº
    -0.19
    ameleon
    -0.18
    容æĺĵ
    -0.18
    éħĭ
    -0.18
    andum
    -0.18
    arrant
    -0.17
    imbus
    -0.17
    享çĶ¨
    -0.17
    èĨĺ
    -0.17
    POSITIVE LOGITS
    /how
    0.23
     اÙĦÙĪاØŃد
    0.22
     somebody
    0.20
    иÑĩ
    0.19
     suddenly
    0.19
    没äºĨ
    0.19
    cox
    0.19
    水管
    0.18
     Somebody
    0.18
    忽çĦ¶
    0.18
    Activations Density 0.086%

    No Known Activations