© 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. 13261
    Prev
    Next
    INDEX
    Explanations

    negative actions and entities

    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
     Mant
    -0.20
    diet
    -0.19
     Amen
    -0.19
    æī¾åĪ°äºĨ
    -0.18
     rebound
    -0.18
    éļħ
    -0.18
    å¯Į
    -0.18
    brands
    -0.18
    _CPP
    -0.18
    æĸ°ä¸ī
    -0.18
    POSITIVE LOGITS
    TF
    0.20
    plash
    0.19
    è´¹çİĩ
    0.18
    ä¸Ńè¶ħ
    0.18
     dipping
    0.18
    aling
    0.18
     Ded
    0.17
    urf
    0.17
    oes
    0.17
     Tops
    0.17
    Activations Density 0.073%

    No Known Activations