© 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. 2669
    Prev
    Next
    INDEX
    Explanations

    delimiters and direct references

    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
    Ĺ
    -0.23
    agem
    -0.23
    涯
    -0.21
    åİŁæłĩé¢ĺ
    -0.21
    mates
    -0.20
     zwar
    -0.20
    /ag
    -0.20
    amide
    -0.20
    ize
    -0.19
     ÑĤоÑĢгов
    -0.19
    POSITIVE LOGITS
    人æĢ§åĮĸ
    0.24
    ä¸įäºĨ
    0.24
    社ä¼ļç»Ħç»ĩ
    0.21
    段æŶéĹ´
    0.21
    å®ŀéĻħè¡ĮåĬ¨
    0.20
    人身
    0.20
    _<
    0.20
    åľ¨ä»ĸçļĦ
    0.20
    ðŁı»
    0.20
    after
    0.20
    Activations Density 0.064%

    No Known Activations