© 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. 1388
    Prev
    Next
    INDEX
    Explanations

    [adjective] way to

    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
     вели
    -0.23
    ity
    -0.22
    aje
    -0.22
    à¹Ģหà¸Ļ
    -0.21
    è¨Ģè¡Į
    -0.21
    bull
    -0.21
    crc
    -0.20
    alen
    -0.20
     нап
    -0.20
    aley
    -0.20
    POSITIVE LOGITS
    tog
    0.26
     anyone
    0.26
    èİ«è¿ĩäºİ
    0.25
     to
    0.24
    ible
    0.23
    ä»»ä½ķ人
    0.23
    çľĭå¾ħ
    0.23
    ä½łåľ¨
    0.23
    åħ¥æīĭ
    0.22
    /place
    0.22
    Activations Density 0.047%

    No Known Activations