© 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. 1650
    Prev
    Next
    INDEX
    Explanations

    citations [pone.XX]

    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
     Clarkson
    -0.23
    Eb
    -0.23
     constexpr
    -0.22
    Cb
    -0.21
    æĿ¥åĪ°äºĨ
    -0.20
    aan
    -0.20
    æĿ¥åĪ°
    -0.20
     systemd
    -0.20
     Boeh
    -0.20
    Activated
    -0.20
    POSITIVE LOGITS
    itas
    0.25
    illum
    0.25
    ç¬Ķè®°
    0.25
    presso
    0.24
    海滩
    0.23
    cape
    0.22
    icle
    0.22
    _EXTRA
    0.22
    onian
    0.22
     SEA
    0.21
    Activations Density 0.016%

    No Known Activations