© 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. 15652
    Prev
    Next
    INDEX
    Explanations

    [optional] / [http/https]

    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
    åŀĤ
    -0.23
    æĪĸå°Ĩ
    -0.20
    é«ĺåľ°
    -0.20
    为æ°ij
    -0.20
    é«ĺä½į
    -0.20
    ework
    -0.19
    çŁ£
    -0.18
    arb
    -0.18
    rab
    -0.18
    ITICAL
    -0.18
    POSITIVE LOGITS
    apons
    0.22
    çĵ¶
    0.19
    主è§Ĵ
    0.18
    éķĩåħļå§Ķ
    0.18
    çĨŁç»ĥ
    0.18
    å²Ĺ
    0.18
     liá»ĩu
    0.18
     Teens
    0.17
    æħĭ
    0.17
    ARAM
    0.17
    Activations Density 0.002%

    No Known Activations