© 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. 465
    Prev
    Next
    INDEX
    Explanations

    fibrillation/fibrils

    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
    åĴ«
    -0.25
    çĪµ
    -0.25
    æ¯Ļ
    -0.23
    speed
    -0.22
     vit
    -0.21
    ,,,,,,,,
    -0.21
    .priv
    -0.21
     recess
    -0.21
    è¿©
    -0.21
    grown
    -0.21
    POSITIVE LOGITS
    å·«
    0.33
    /community
    0.23
    obre
    0.22
     Gri
    0.22
    /bash
    0.22
    éľ²å¤©
    0.22
    èıĮ
    0.22
    亢
    0.22
    /configuration
    0.21
    obile
    0.21
    Activations Density 0.023%

    No Known Activations