© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 266
    Prev
    Next
    INDEX
    Explanations

    vacant jobs and vacancies

    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
    ç²¾å¿ĥ
    -0.23
    SON
    -0.20
    MOST
    -0.20
    æħĮ
    -0.20
    IGHT
    -0.20
    yth
    -0.20
    phem
    -0.19
    ystone
    -0.19
    /he
    -0.19
     expansive
    -0.19
    POSITIVE LOGITS
    æľŁåĨħ
    0.23
    æ®Ĩ
    0.23
    cies
    0.23
    åıĹçIJĨ
    0.23
    èĶ¬
    0.22
    /lic
    0.22
    ngo
    0.21
    /dis
    0.21
    /errors
    0.20
    ä¿¡æģ¯åıijå¸ĥ
    0.20
    Activations Density 0.005%

    No Known Activations