© 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. 11738
    Prev
    Next
    INDEX
    Explanations

    -able / -ending / -amend / -amusing / -emblem suffix

    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
    ï¸ı
    -0.19
    ani
    -0.19
    amm
    -0.18
    acles
    -0.18
    Svc
    -0.17
    izzazione
    -0.17
     Mighty
    -0.17
    spin
    -0.17
    kl
    -0.17
    ол
    -0.17
    POSITIVE LOGITS
    IDER
    0.21
    çªģåĩºéĹ®é¢ĺ
    0.21
    odox
    0.18
     обÑĭ
    0.18
     ëĵ¤
    0.18
    _fa
    0.18
    spb
    0.17
    IDEO
    0.17
    nbr
    0.17
     Minimal
    0.17
    Activations Density 0.486%

    No Known Activations