© 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. 1163
    Prev
    Next
    INDEX
    Explanations

    names after commas and 'and'

    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
     ForCanBeConvertedToForeach
    -0.29
    dos
    -0.26
    ORIES
    -0.24
     disarm
    -0.24
     ghetto
    -0.23
    Cad
    -0.23
    UEL
    -0.23
    cesso
    -0.23
    Dos
    -0.23
    /address
    -0.22
    POSITIVE LOGITS
     Robert
    0.39
     J
    0.36
     Edward
    0.33
     M
    0.33
     N
    0.32
     Param
    0.31
     Ship
    0.31
     L
    0.31
     Jr
    0.30
     John
    0.30
    Activations Density 0.080%

    No Known Activations