© 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. 462
    Prev
    Next
    INDEX
    Explanations

    down with combinations

    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
    ALLY
    -0.23
    ÑĥÑī
    -0.22
    urch
    -0.21
    udes
    -0.19
    emony
    -0.19
    Ĥ¬
    -0.19
     Stall
    -0.19
    貫
    -0.19
     ongoing
    -0.19
    ijľ
    -0.18
    POSITIVE LOGITS
    graded
    0.25
    ness
    0.24
    æĢ§çĸ¾çĹħ
    0.24
    ward
    0.23
    ey
    0.23
    manship
    0.22
    -down
    0.22
    bye
    0.21
    most
    0.21
    side
    0.21
    Activations Density 0.016%

    No Known Activations