© 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. 750
    Prev
    Next
    INDEX
    Explanations

    tapered, rectangular, ovoidal shapes

    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
    æįĨç»ij
    -0.24
    æįĨ
    -0.24
    orks
    -0.23
     Miles
    -0.23
    stration
    -0.23
    Buzz
    -0.22
    åħ¬ç«ĭ
    -0.22
    .ef
    -0.22
    ymbols
    -0.22
    管ç½ij
    -0.21
    POSITIVE LOGITS
    åŀĭ
    0.31
    -,
    0.26
    -d
    0.25
    -l
    0.25
    -leaning
    0.24
    -ish
    0.23
    edor
    0.23
     Remarks
    0.23
     оÑĩеÑĢ
    0.23
    åĿ³
    0.23
    Activations Density 0.032%

    No Known Activations