© 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. 13268
    Prev
    Next
    INDEX
    Explanations

    detective or undercover

    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
    ings
    -0.20
    nings
    -0.19
    Balancer
    -0.19
    èĩ¾
    -0.17
    edList
    -0.17
    ãģ£ãģ±
    -0.17
    éªĭ
    -0.17
    ulk
    -0.17
    éļıæīĭ
    -0.16
    walls
    -0.16
    POSITIVE LOGITS
    åıĸè¯ģ
    0.17
    crm
    0.17
    çłĶ究表æĺİ
    0.16
    blo
    0.16
    utorial
    0.16
    ÑĢоÑģ
    0.16
    å·¥ä½ľçļĦ
    0.16
     crime
    0.16
    ype
    0.15
    راÙĨ
    0.15
    Activations Density 0.004%

    No Known Activations