© 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. 11943
    Prev
    Next
    INDEX
    Explanations

    I said

    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
    orth
    -0.23
    AMI
    -0.20
    igan
    -0.20
    RT
    -0.20
    éĤ£å°±æĺ¯
    -0.19
    éĺľ
    -0.19
     RB
    -0.19
    ***
    -0.19
    uf
    -0.19
     Hil
    -0.19
    POSITIVE LOGITS
    以ä¸ĬçļĦ
    0.31
    以ä¸Ĭ
    0.29
    è¿ĻäºĽéĥ½æĺ¯
    0.29
    以ä¸Ĭãģ®
    0.26
    bove
    0.23
    Above
    0.23
    _above
    0.23
    è¿ĻäºĽéĹ®é¢ĺ
    0.23
     above
    0.23
    above
    0.23
    Activations Density 0.381%

    No Known Activations