© 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. 13047
    Prev
    Next
    INDEX
    Explanations

    microbes and microorganisms

    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
    âīĤ
    -0.34
    íĹĢ
    -0.33
    PropertyParams
    -0.27
    numerusform
    -0.27
    gMaps
    -0.27
     geschichten
    -0.26
    медиÑĨинÑģк
    -0.26
     miÄĻd
    -0.26
     mükem
    -0.25
     erotisk
    -0.25
    POSITIVE LOGITS
     bacteria
    0.35
     organisms
    0.32
    èıĮ
    0.31
    å¾®çĶŁçī©
    0.31
    åħ±çĶŁ
    0.28
     gram
    0.27
    ç»ĨèıĮ
    0.26
     colonies
    0.26
    ç¹ģæ®ĸ
    0.26
     strains
    0.25
    Activations Density 0.511%

    No Known Activations