© 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. 2624
    Prev
    Next
    INDEX
    Explanations

    text formatting tags (`<b>`, `<i>`, `<code>`)

    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
    ç»ĦåĽ¾
    -0.26
    singleton
    -0.26
    ä¸Ģå¥Ĺ
    -0.25
    ä¸ĢçŃīå¥ĸ
    -0.23
    ä¿Ŀå§Ĩ
    -0.23
    梯éĺŁ
    -0.22
     Herb
    -0.21
     depths
    -0.21
     prow
    -0.20
    rab
    -0.20
    POSITIVE LOGITS
    inded
    0.27
    .fil
    0.26
    ilit
    0.24
    anden
    0.22
    nier
    0.22
    orate
    0.22
    å¶
    0.22
    Toolkit
    0.21
    licative
    0.21
    еле
    0.21
    Activations Density 0.032%

    No Known Activations