© 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. 2585
    Prev
    Next
    INDEX
    Explanations

    person/group size and composition

    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
    обÑĢа
    -0.24
    etes
    -0.22
     protester
    -0.22
    /Instruction
    -0.22
    igrams
    -0.21
    Occurrences
    -0.21
    erea
    -0.21
     thinker
    -0.21
    ollect
    -0.20
    é¢Ļ
    -0.20
    POSITIVE LOGITS
    éĺŁä¼į
    0.31
    dü
    0.27
    èĪ°éĺŁ
    0.26
    è£Ļ
    0.25
    è¡ĮåĪĹ
    0.25
    åĽ½åľŁ
    0.24
     society
    0.24
    æĪĸå¤ļ
    0.24
    大éĺŁ
    0.23
     tempList
    0.23
    Activations Density 0.014%

    No Known Activations