© 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. 14570
    Prev
    Next
    INDEX
    Explanations

    threshold, half-life, pKa

    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
     Nights
    -0.19
    .python
    -0.19
    æľīæľºä¼ļ
    -0.19
     Oracle
    -0.18
    沿çĿĢ
    -0.18
    è¯Ħæ¯Ķ
    -0.17
    èıģ
    -0.17
    room
    -0.17
    åħ¨ä½ĵ
    -0.17
    łģ
    -0.17
    POSITIVE LOGITS
    åĢ¼
    0.24
    çĤ¹
    0.23
    PCS
    0.22
    éĺĪ
    0.22
    éĹ¨æ§Ľ
    0.21
     threshold
    0.21
    åľ¨åĵªéĩĮ
    0.20
    éĩľ
    0.20
    Dst
    0.20
    punkt
    0.20
    Activations Density 0.247%

    No Known Activations