© 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. 2843
    Prev
    Next
    INDEX
    Explanations

    past visits and times

    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
    çķ´
    -0.25
    æijĺç¼ĸ
    -0.24
    éĶ·
    -0.23
    å¼ij
    -0.23
    ä¸ĢåĪĨ
    -0.22
    æĹ¥çĶµ
    -0.22
    弩
    -0.22
     Omni
    -0.22
     assignable
    -0.22
     yazılı
    -0.21
    POSITIVE LOGITS
     visit
    0.36
     visits
    0.33
    æľĢåIJİä¸Ģ次
    0.32
    åĩłæ¬¡
    0.31
    次æķ°
    0.30
    visit
    0.30
    Visit
    0.30
    两次
    0.29
     visita
    0.28
     revisit
    0.28
    Activations Density 0.026%

    No Known Activations