© 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. 11767
    Prev
    Next
    INDEX
    Explanations

    ammonia and ammonium

    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
    ģ
    -0.17
    -0.17
    unde
    -0.17
    oci
    -0.16
    ided
    -0.16
    ship
    -0.15
    undry
    -0.15
    ¬
    -0.15
    anded
    -0.15
    endl
    -0.15
    POSITIVE LOGITS
    ments
    0.25
    çĦ¶æĺ¯
    0.20
    MENT
    0.17
    ất
    0.16
    ingly
    0.16
    entai
    0.16
    çīĸ
    0.16
    év
    0.15
    /dr
    0.15
    /oct
    0.15
    Activations Density 0.014%

    No Known Activations