© 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. 2336
    Prev
    Next
    INDEX
    Explanations

    information encoding and storage

    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
    æ²¥
    -0.27
     Manit
    -0.26
     coment
    -0.25
     recommendations
    -0.25
    æݨèįIJ
    -0.25
     monthly
    -0.24
     hourly
    -0.24
     undocumented
    -0.23
     aft
    -0.23
    ocop
    -0.23
    POSITIVE LOGITS
    Encoding
    0.48
     Encoding
    0.44
     encoded
    0.43
     binary
    0.43
     encoding
    0.42
     encode
    0.40
    åĻ¨ä»¶
    0.39
     programm
    0.38
    çĶµè·¯
    0.38
     Binary
    0.37
    Activations Density 0.434%

    No Known Activations