© 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. 653
    Prev
    Next
    INDEX
    Explanations

    production company / manager / needs

    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
    oug
    -0.23
    adow
    -0.22
    ActionCode
    -0.21
     positional
    -0.20
    NESS
    -0.20
    ä¸Ģ个éĩįè¦ģ
    -0.20
     potent
    -0.20
    å¾Īå¤ļ
    -0.19
    andom
    -0.19
    hood
    -0.19
    POSITIVE LOGITS
    istrator
    0.27
    eer
    0.25
    äºĭå®ľ
    0.24
    ned
    0.23
    ists
    0.22
    yards
    0.22
    -wise
    0.22
    -ready
    0.21
     underway
    0.21
    -scale
    0.21
    Activations Density 0.022%

    No Known Activations