© 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. 658
    Prev
    Next
    INDEX
    Explanations

    growing to a measurement or state

    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
    该åī§
    -0.29
    è¿ĻæĶ¯
    -0.27
    客
    -0.24
    ASS
    -0.24
    fabric
    -0.23
    æķ´ä¸ªäºº
    -0.23
    åİŁæĿIJæĸĻ
    -0.23
    å»īä»·
    -0.22
    .Big
    -0.22
    ={}
    -0.22
    POSITIVE LOGITS
     maturity
    0.28
     equilibrium
    0.28
     desired
    0.26
    °C
    0.25
     point
    0.24
     peak
    0.24
     temperature
    0.24
     temperatures
    0.24
     specified
    0.23
    iking
    0.23
    Activations Density 0.003%

    No Known Activations