© 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. 2788
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    thro
    -0.21
    tram
    -0.20
    åIJİ代
    -0.19
    çĤĻ
    -0.19
    PING
    -0.18
    pee
    -0.18
    thing
    -0.18
    Baseline
    -0.18
     baseline
    -0.18
    ç®Ģ便
    -0.18
    POSITIVE LOGITS
    ä»Ģä¹ĪåİŁåĽł
    0.30
    éĽĦåİļ
    0.23
    holder
    0.23
    hift
    0.22
    olutely
    0.22
    æĸ¼
    0.21
    camp
    0.20
    lee
    0.20
    º
    0.20
    numer
    0.19
    Activations Density 0.124%

    No Known Activations