© 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. 11788
    Prev
    Next
    INDEX
    Explanations

    building on

    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
    å½ĵä¹ĭæĹłæĦ§
    -0.25
    anking
    -0.23
     miÄĻd
    -0.20
    ags
    -0.19
    缮çļĦæĺ¯
    -0.19
    ByPrimaryKey
    -0.19
    liness
    -0.19
    olean
    -0.19
    )did
    -0.19
    agnostics
    -0.19
    POSITIVE LOGITS
    以å¾Ģ
    0.31
    åİŁæľīçļĦ
    0.31
    çİ°æľīçļĦ
    0.29
     existing
    0.27
     previous
    0.27
    èĩªèº«çļĦ
    0.26
     previously
    0.25
    åħĪåīį
    0.25
    åİŁæľī
    0.25
    å¾Ģå¹´
    0.25
    Activations Density 0.027%

    No Known Activations