© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 801
    Prev
    Next
    INDEX
    Explanations

    intent or configuration blocks

    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
    __',
    -0.22
     @$
    -0.22
    Gay
    -0.22
    andas
    -0.21
     Gay
    -0.21
    å°ĨåĨĽ
    -0.20
    æĭľ
    -0.20
    éĺ³
    -0.20
    wald
    -0.20
    lider
    -0.20
    POSITIVE LOGITS
    Unnamed
    0.25
     ReturnType
    0.24
     happiest
    0.22
     Transparency
    0.22
    reasonable
    0.22
    adors
    0.21
    è±®
    0.21
     ASAP
    0.21
     Legislature
    0.21
     OPTIONAL
    0.21
    Activations Density 0.423%

    No Known Activations