© 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. 1424
    Prev
    Next
    INDEX
    Explanations

    swap or slot tokens

    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
    ãĤĤãģ®
    -0.26
     intermittent
    -0.21
    yaw
    -0.21
    ãĥ£
    -0.21
    slope
    -0.20
    ugo
    -0.20
    sword
    -0.20
    yen
    -0.20
    eing
    -0.20
    WA
    -0.19
    POSITIVE LOGITS
    tures
    0.23
    åĴĮ个人
    0.22
    mates
    0.21
    ä¸įæ¸ħ
    0.21
    pered
    0.19
    ieties
    0.19
    Ø·
    0.19
    ting
    0.18
    rint
    0.18
    è´©
    0.18
    Activations Density 0.009%

    No Known Activations