© 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. 16780
    Prev
    Next
    INDEX
    Explanations

    sole followed by noun

    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
    éķ¿æķĪæľºåĪ¶
    -0.19
     Mature
    -0.18
    ough
    -0.17
    OUGH
    -0.17
    å°ijä¸įäºĨ
    -0.16
    åĨħåľ°
    -0.16
    _prefs
    -0.16
    çķ´
    -0.16
    /rem
    -0.15
    usercontent
    -0.15
    POSITIVE LOGITS
    ridge
    0.24
    åľŃ
    0.20
    ë°ķ
    0.20
    ify
    0.20
    人士
    0.18
    éºŁ
    0.18
    ÙĪÙĬØ©
    0.17
    ãģĹãģĭãĤĤ
    0.17
    casting
    0.17
    ship
    0.17
    Activations Density 0.002%

    No Known Activations