© 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. 15749
    Prev
    Next
    INDEX
    Explanations

    weight and size measurements

    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
    çĻ«
    -0.20
    éļıæīĭ
    -0.20
    åı¯æݧ
    -0.19
    éļıå¤Ħåı¯è§ģ
    -0.19
    è¿«
    -0.19
     sop
    -0.19
    æݧ
    -0.19
    éļĻ
    -0.18
    åĢŁéĴ±
    -0.18
    ä¸ĭåİ»
    -0.18
    POSITIVE LOGITS
    身躯
    0.21
    å¾Īæ¼Ĥ亮
    0.20
    _record
    0.20
    ãĤµãĤ¤ãĤº
    0.20
    -sized
    0.20
    åĪĽä¸ĭ
    0.19
    filesize
    0.19
    ArgumentException
    0.19
    omid
    0.19
    第äºĮ大
    0.18
    Activations Density 0.010%

    No Known Activations