© 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. 2432
    Prev
    Next
    INDEX
    Explanations

    verification of identity details

    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
    :///
    -0.24
    Maker
    -0.24
    ï¸
    -0.23
     Fil
    -0.22
    ä¼´ä¾£
    -0.21
    phans
    -0.21
    .clone
    -0.21
    yyy
    -0.20
     Rah
    -0.20
    å°ıçĻ½
    -0.20
    POSITIVE LOGITS
     validity
    0.27
    æł¸å®ŀ
    0.25
     eligibility
    0.24
     correctness
    0.24
     ок
    0.23
    åı£åij³
    0.23
    ActionResult
    0.22
    确认
    0.22
    TURE
    0.22
    éĢīå®ļ
    0.22
    Activations Density 0.008%

    No Known Activations