© 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. 1924
    Prev
    Next
    INDEX
    Explanations

    pass to hit or land

    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
    æľįå½¹
    -0.28
    cult
    -0.27
     ratings
    -0.26
     enroll
    -0.26
    å§Ĵ
    -0.26
     Cult
    -0.25
    çĨ¬
    -0.25
    strup
    -0.25
     hired
    -0.24
     enrol
    -0.24
    POSITIVE LOGITS
    ä¼łçIJĥ
    0.36
     momentarily
    0.33
    çŀ¬éĹ´
    0.32
    精彩çļĦ
    0.32
    åĩ»
    0.30
    éĤ£æ¬¡
    0.29
     angled
    0.29
    æĬ¢æķij
    0.29
     missed
    0.28
     interception
    0.28
    Activations Density 0.040%

    No Known Activations