© 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. 2168
    Prev
    Next
    INDEX
    Explanations

    import tax or service

    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
     undercover
    -0.28
    éĢłåģĩ
    -0.26
     roundup
    -0.24
     reward
    -0.24
    æľ¬èº«
    -0.23
    AtIndex
    -0.23
    @stop
    -0.23
    _trap
    -0.23
     days
    -0.23
    -target
    -0.23
    POSITIVE LOGITS
     DAM
    0.27
    _scaling
    0.25
     DAMAGE
    0.25
    æ²Ļåıij
    0.24
     uphol
    0.23
    ulling
    0.23
    agus
    0.23
     upholstery
    0.23
    [input
    0.22
    NAV
    0.22
    Activations Density 0.002%

    No Known Activations