© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 982
    Prev
    Next
    INDEX
    Explanations

    checks, balances, branches, unchecked

    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
    ity
    -0.24
     sky
    -0.24
    èģĬ
    -0.23
    eventType
    -0.23
    undry
    -0.23
     mbox
    -0.22
     updatedAt
    -0.22
    åľºæĻ¯
    -0.22
    atica
    -0.22
    ä¸ĢæľŁ
    -0.22
    POSITIVE LOGITS
    æľºåĪ¶
    0.39
     mechanism
    0.33
    åĪ¶çº¦
    0.30
     mechanisms
    0.28
     меÑħанизм
    0.27
    /control
    0.27
    çĽijçĿ£
    0.25
    å¨ģæħij
    0.25
     imposed
    0.25
    åĬĽéĩı
    0.25
    Activations Density 0.004%

    No Known Activations