© 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. 2822
    Prev
    Next
    INDEX
    Explanations

    comparison

    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
    è¿ŀèĥľ
    -0.25
    ä¸įä»ħä»ħæĺ¯
    -0.23
     brief
    -0.23
    线
    -0.23
    ä¸įä»ħä»ħ
    -0.23
    ä¸įåĨįæĺ¯
    -0.22
    ä¸ºæł¸å¿ĥ
    -0.22
    æľ«
    -0.22
    èĹī
    -0.22
    ä¸įåĨį
    -0.22
    POSITIVE LOGITS
     than
    0.31
    RequestId
    0.28
    _than
    0.26
    -than
    0.26
    å®ŀéĻħæĥħåĨµ
    0.24
    éĤ£äºĽ
    0.24
     pumped
    0.24
    å¹³åĿĩæ°´å¹³
    0.24
    ozo
    0.23
    Than
    0.23
    Activations Density 0.033%

    No Known Activations