© 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. 14856
    Prev
    Next
    INDEX
    Explanations

    number of children

    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
    åŁºåĩĨ
    -0.21
    оÑĢа
    -0.18
    æĬ½
    -0.18
    itet
    -0.17
    oria
    -0.17
    _('
    -0.17
    STALL
    -0.17
    ields
    -0.17
    èĵij
    -0.17
    arez
    -0.17
    POSITIVE LOGITS
    交代
    0.21
    å®Ŀè´Ŀ
    0.21
    andi
    0.19
    åĿĩå·²
    0.19
    活泼
    0.18
    éķĴ
    0.18
    ç¾İ好çĶŁæ´»
    0.18
    Wi
    0.18
    åī¡
    0.18
     Wi
    0.18
    Activations Density 0.016%

    No Known Activations