© 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. 16820
    Prev
    Next
    INDEX
    Explanations

    circumstances

    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
    onomy
    -0.22
    ish
    -0.20
    -0.18
    åĮĸè¿Ľç¨ĭ
    -0.18
    çĽı
    -0.18
    Äħc
    -0.18
    说æĺ¯
    -0.17
    itionally
    -0.16
    hammer
    -0.16
    bies
    -0.16
    POSITIVE LOGITS
     circumstances
    0.27
    ester
    0.20
    ous
    0.20
    ally
    0.20
     conditions
    0.19
    etr
    0.19
     circumstance
    0.18
    æĿ¡ä»¶
    0.18
    esa
    0.18
    ously
    0.18
    Activations Density 0.007%

    No Known Activations