© 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. 2350
    Prev
    Next
    INDEX
    Explanations

    extent, coverage, or range

    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
    ded
    -0.23
    Appearance
    -0.23
    fax
    -0.23
     forwarded
    -0.22
    atum
    -0.21
    SED
    -0.21
    çŁ³èĨı
    -0.21
     reli
    -0.21
    æķ°æݧ
    -0.21
    adies
    -0.21
    POSITIVE LOGITS
    èĮĥåĽ´
    0.52
     scope
    0.47
     scopes
    0.43
    è§Ĩéĩİ
    0.42
    广éĺĶ
    0.42
     encompass
    0.42
    å¼ĢéĺĶ
    0.42
    -wide
    0.41
    广éĺĶçļĦ
    0.41
     breadth
    0.41
    Activations Density 0.161%

    No Known Activations