© 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. 1584
    Prev
    Next
    INDEX
    Explanations

    mushroom or hippocampus

    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
    hton
    -0.23
    rib
    -0.23
    ibles
    -0.21
    soever
    -0.21
    ities
    -0.21
    resse
    -0.20
    loys
    -0.19
    -AA
    -0.19
    ohl
    -0.18
    æ³Ĭ
    -0.18
    POSITIVE LOGITS
    er
    0.29
    sWith
    0.26
    ed
    0.26
    swith
    0.24
    ing
    0.24
    screen
    0.23
    sj
    0.22
    ally
    0.22
    sz
    0.22
    scale
    0.22
    Activations Density 0.018%

    No Known Activations