© 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. 2083
    Prev
    Next
    INDEX
    Explanations

    evolutionary topics

    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
    ness
    -0.31
    å¤ĸçķĮ
    -0.24
    NESS
    -0.21
    .getvalue
    -0.21
    lds
    -0.20
    rets
    -0.20
    оÑģÑĤÑĮ
    -0.20
    etails
    -0.20
    dle
    -0.20
    ots
    -0.19
    POSITIVE LOGITS
    -minded
    0.29
    -themed
    0.28
    -inspired
    0.28
    -related
    0.27
     minded
    0.26
    ationally
    0.24
    -era
    0.24
    -derived
    0.23
    ually
    0.23
    åŃ¦å®¶
    0.22
    Activations Density 0.018%

    No Known Activations