© 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. 2205
    Prev
    Next
    INDEX
    Explanations

    current or present status

    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
     nonsense
    -0.24
    nett
    -0.22
     crossorigin
    -0.22
    неÑĤ
    -0.22
    SessionFactory
    -0.21
     coherence
    -0.21
    objective
    -0.21
    fax
    -0.21
    onomy
    -0.21
    ãĥijãĤ¿ãĥ¼ãĥ³
    -0.21
    POSITIVE LOGITS
     enrolled
    0.31
     member
    0.28
     regular
    0.26
    (active
    0.26
     members
    0.26
     active
    0.26
    -active
    0.25
    eph
    0.25
    ä½ıæĪ·
    0.24
    .getActive
    0.24
    Activations Density 0.019%

    No Known Activations