© 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. 1558
    Prev
    Next
    INDEX
    Explanations

    dream sequences

    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
    redo
    -0.21
    æĭ¯
    -0.19
    åıijå±ķæ½ľåĬĽ
    -0.19
     mắc
    -0.19
    <cv
    -0.19
    auen
    -0.18
    rowing
    -0.18
    _TYPED
    -0.18
    OrCreate
    -0.17
     denn
    -0.17
    POSITIVE LOGITS
    er
    0.34
    iest
    0.29
    ers
    0.28
    maker
    0.27
    ing
    0.26
    less
    0.26
    iness
    0.26
    able
    0.26
    ling
    0.25
    liness
    0.25
    Activations Density 0.010%

    No Known Activations