© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 328
    Prev
    Next
    INDEX
    Explanations

    answering machines and messages

    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
    æĴ¸
    -0.27
     vess
    -0.25
    plorer
    -0.23
    azo
    -0.23
    æĶ¹éĿ©
    -0.22
    _Msk
    -0.22
    _dependency
    -0.22
    åīĸ
    -0.22
     hood
    -0.22
     heated
    -0.22
    POSITIVE LOGITS
    å½ķåĪ¶
    0.37
    éŁ³é¢ij
    0.36
    å½ķéŁ³
    0.36
    è¯ŃéŁ³
    0.36
     recordings
    0.34
     message
    0.33
     phone
    0.32
    çĶµè¯Ŀ
    0.32
    PhoneNumber
    0.31
     tapes
    0.31
    Activations Density 0.011%

    No Known Activations