© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2834
    Prev
    Next
    INDEX
    Explanations

    lists of components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    åĩłå®¶
    -0.26
    åħ¬çĦ¶
    -0.25
    两ç§į
    -0.25
    åĩłç§į
    -0.24
    oming
    -0.24
     parked
    -0.24
    ordin
    -0.23
    çŃīå¤ļç§į
    -0.22
    _patterns
    -0.22
    ä¸īæĿ¡
    -0.22
    POSITIVE LOGITS
    æĶ¯æŁ±
    0.26
    åĪĨåĪ«æĺ¯
    0.25
    cxx
    0.25
    å±ŀæĢ§
    0.24
    ä¹ĭä¸Ģ
    0.23
     PU
    0.23
    :
    0.23
     viz
    0.23
    ffd
    0.22
    æĬĵ好
    0.22
    Activations Density 0.053%

    No Known Activations