© 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. 16867
    Prev
    Next
    INDEX
    Explanations

    transistor

    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
    纬
    -0.27
    AtA
    -0.24
    èĪ·
    -0.24
     fkk
    -0.24
    esktop
    -0.23
    éĮ¾
    -0.22
    	RTLR
    -0.22
    åĨ»
    -0.22
    å§Ķ
    -0.22
    绳
    -0.22
    POSITIVE LOGITS
    åĻ¨ä»¶
    0.30
    ç»ĵæŀĦ
    0.24
     devices
    0.24
     device
    0.23
    çĶµè·¯
    0.23
     structure
    0.21
     chip
    0.21
     ÑĥÑģÑĤÑĢой
    0.21
    èķĬ
    0.21
     cell
    0.20
    Activations Density 0.582%

    No Known Activations