© 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. 2495
    Prev
    Next
    INDEX
    Explanations

    oh you

    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
    çĿ¥
    -0.22
    äºĨ大éĩıçļĦ
    -0.21
    ipt
    -0.20
    enance
    -0.20
    éĢĨè¢Ń
    -0.20
    ä¸ĢåįĬ
    -0.19
    алÑĮн
    -0.19
    åĪ»èĭ¦
    -0.19
    ivor
    -0.19
    alph
    -0.19
    POSITIVE LOGITS
    lymp
    0.26
    rame
    0.24
    icial
    0.23
    ãģĦãģ£ãģŁ
    0.23
    že
    0.23
     bother
    0.22
    mitted
    0.22
    deal
    0.22
    è¡·
    0.21
    lic
    0.21
    Activations Density 0.014%

    No Known Activations