© 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. 15796
    Prev
    Next
    INDEX
    Explanations

    actions done to others or for others

    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
    tank
    -0.19
     tank
    -0.19
    rium
    -0.18
    rollers
    -0.18
     VO
    -0.17
    emies
    -0.17
     egreg
    -0.17
    à¹Ĥรà¸ĩà¸ŀ
    -0.17
    /he
    -0.17
    ä¸İæĹ¶ä¿±è¿Ľ
    -0.17
    POSITIVE LOGITS
    ä¹ĭåħ§å®¹
    0.20
    çī¹æĿĥ
    0.19
    åĬłä¹ĭ
    0.18
    osal
    0.18
     Roo
    0.18
    à¹Ģà¸Ń
    0.17
    åħ¨è¿ĩç¨ĭ
    0.17
    åģ¶å°Ķ
    0.17
    éĩijåĪļ
    0.17
    建èŃ°
    0.17
    Activations Density 0.082%

    No Known Activations