© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1418
    Prev
    Next
    INDEX
    Explanations

    based on differences

    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
    elman
    -0.28
    oste
    -0.24
    çļĦæīĢæľī
    -0.23
    stead
    -0.23
     Shortcut
    -0.23
    airo
    -0.23
    åħ¨å¤©
    -0.22
    çĻ½å¤©
    -0.22
    minster
    -0.22
    ç¼ĵæħ¢
    -0.22
    POSITIVE LOGITS
    åĮºåĪĨ
    0.51
     differences
    0.44
     differentiation
    0.43
     distinctions
    0.40
    å·®å¼Ĥ
    0.39
     Differences
    0.38
    åĪĴåĪĨ
    0.37
     differentiate
    0.36
    åĮºåĪ«
    0.35
    å·®åĪ«
    0.34
    Activations Density 0.255%

    No Known Activations