© 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. 13866
    Prev
    Next
    INDEX
    Explanations

    bring about / out / you

    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
    -0.20
    HING
    -0.16
    åı¯æĥ³
    -0.16
    è¦ģæĬĬ
    -0.15
    缼å¼Ģ
    -0.15
    æŃ£å¸¸ä½¿çĶ¨
    -0.15
    thetic
    -0.15
    èĻ±
    -0.15
    /rules
    -0.15
    ocus
    -0.15
    POSITIVE LOGITS
    ings
    0.21
    holding
    0.20
     forth
    0.19
    -around
    0.18
    -up
    0.17
    好å¤Ħ
    0.17
    -out
    0.17
    ±
    0.17
    INGS
    0.17
     elkaar
    0.17
    Activations Density 0.022%

    No Known Activations