© 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. 2636
    Prev
    Next
    INDEX
    Explanations

    extinct species or genera

    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
    Ñĩик
    -0.24
    ðŁı»
    -0.20
    ments
    -0.20
    cci
    -0.20
    è´´è¿ij
    -0.20
    -Benz
    -0.20
    çıı
    -0.20
     frei
    -0.20
    hti
    -0.20
    csi
    -0.19
    POSITIVE LOGITS
    çī©ç§į
    0.24
    esimal
    0.24
     species
    0.24
    uary
    0.22
    /un
    0.22
    .species
    0.21
    reate
    0.21
    forms
    0.21
    species
    0.20
    -minded
    0.20
    Activations Density 0.004%

    No Known Activations