© 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. 1263
    Prev
    Next
    INDEX
    Explanations

    occupy and variations

    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
    bei
    -0.23
    ê»ĺ
    -0.21
    ater
    -0.21
    eling
    -0.20
    ply
    -0.20
    leccion
    -0.19
    mts
    -0.19
     تعاÙĦÙī
    -0.18
    inks
    -0.18
    ATER
    -0.18
    POSITIVE LOGITS
    eer
    0.27
    e
    0.26
     Ñģобой
    0.24
    /or
    0.23
    cy
    0.20
    eur
    0.20
    eil
    0.19
    cies
    0.19
    çĮİ
    0.18
    rats
    0.18
    Activations Density 0.028%

    No Known Activations