© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3276
    Prev
    Next
    INDEX
    Explanations

    already followed by a past participle or indicating prior state

    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
    Negative Logits
    åİŁä»¶
    -0.23
    inium
    -0.22
    raries
    -0.22
    ä¸Ńæĸ°
    -0.22
    ä»ħä¾Ľ
    -0.22
    pong
    -0.22
    è¿ľæĻ¯
    -0.21
    etically
    -0.21
    éĻ¤æѤä¹ĭå¤ĸ
    -0.21
    lets
    -0.20
    POSITIVE LOGITS
    mente
    0.31
    æľīä¸įå°ij
    0.25
    -fashioned
    0.24
    thought
    0.23
    hand
    0.22
    -born
    0.22
    chaft
    0.21
     been
    0.21
    æľīå¾Īå¤ļ
    0.21
    quite
    0.21
    Activations Density 0.025%

    No Known Activations