© 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. 2315
    Prev
    Next
    INDEX
    Explanations

    happy medium, tail, valley, patients, days

    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»IJ
    -0.25
    æŀģé«ĺ
    -0.23
     PREF
    -0.23
    ervo
    -0.23
    iesz
    -0.23
    edm
    -0.22
    uset
    -0.22
    riv
    -0.21
    £¼
    -0.21
    ied
    -0.21
    POSITIVE LOGITS
    æ¶Ī
    0.24
    ðŁı»
    0.23
    (lower
    0.23
    åĢĻ
    0.23
    ä¸ĭåįĪ
    0.22
     lunch
    0.22
     ambiance
    0.22
     breakfast
    0.22
     activate
    0.21
    æIJŃ
    0.21
    Activations Density 0.002%

    No Known Activations