© 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. 15730
    Prev
    Next
    INDEX
    Explanations

    cleaning actions and agents

    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
    ively
    -0.22
    ä¸Ģçŀ¬éĹ´
    -0.18
    ness
    -0.18
    quis
    -0.17
    ably
    -0.17
    ivity
    -0.17
    ç¾İæĦŁ
    -0.17
    çķ¦
    -0.17
    ted
    -0.17
    ually
    -0.17
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.23
    æķ´é¡¿
    0.22
    åijĺ
    0.22
    å®Įæ¯ķ
    0.20
    ä¸İåıijå±ķ
    0.19
    åĵ¡
    0.19
    еÑģ
    0.18
    çĿ¬
    0.18
    çĸıéĢļ
    0.17
    bourne
    0.17
    Activations Density 0.015%

    No Known Activations