© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14653
    Prev
    Next
    INDEX
    Explanations

    natural and historical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     pornost
    -0.26
    oppable
    -0.23
     ragaz
    -0.23
    åħħå®ŀ
    -0.23
    人éĢī
    -0.21
    âīĤ
    -0.21
    ãįij
    -0.20
     wida
    -0.20
    äºĭåħĪ
    -0.20
     salopes
    -0.20
    POSITIVE LOGITS
    èĩªçĦ¶
    0.37
     natural
    0.33
    天çĦ¶
    0.31
    è¿ij代
    0.30
     naturally
    0.29
    natural
    0.28
    Natural
    0.28
    çݰ代
    0.25
     natur
    0.25
     doÄŁal
    0.24
    Activations Density 0.046%

    No Known Activations