© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13576
    Prev
    Next
    INDEX
    Explanations

    reading file content as bytes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    FilterWhere
    -0.35
    actionDate
    -0.32
    PropertyParams
    -0.30
    mPid
    -0.27
    usra
    -0.27
     principalColumn
    -0.26
    BitFields
    -0.26
    gMaps
    -0.24
     iNdEx
    -0.24
    ParallelGroup
    -0.24
    POSITIVE LOGITS
    contents
    0.37
     contents
    0.36
    åĨħ容
    0.35
     content
    0.31
    content
    0.31
     bytes
    0.30
     ÑģодеÑĢж
    0.29
     ëĤ´ìļ©
    0.28
    _CONTENT
    0.27
    chunk
    0.26
    Activations Density 0.777%

    No Known Activations