© 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. 1448
    Prev
    Next
    INDEX
    Explanations

    paths combined or laundry add

    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
    ate
    -0.25
    ç®į
    -0.24
    æ¶Ĥ
    -0.24
    iso
    -0.24
    å¤ĸå¢Ļ
    -0.22
     Cooper
    -0.22
    äºĨ解
    -0.22
    åĻ©
    -0.21
    /MPL
    -0.21
    POSITIVE LOGITS
    æĶ¾åħ¥
    0.42
    åľ¨éĩĮéĿ¢
    0.36
    æĶ¾è¿Ľ
    0.35
    åĬłåħ¥
    0.34
    åľ¨ä¸Ģèµ·
    0.33
    ãĤĴåħ¥ãĤĮ
    0.32
     together
    0.32
     addObject
    0.31
    .addAll
    0.31
     Together
    0.31
    Activations Density 0.263%

    No Known Activations