© 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. 12121
    Prev
    Next
    INDEX
    Explanations

    women or girls

    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
     converted
    -0.18
    客è§Ĥ
    -0.18
     rit
    -0.17
    å»¶æľŁ
    -0.17
    ddl
    -0.17
    isl
    -0.17
    decess
    -0.17
    eneg
    -0.17
    ecs
    -0.17
    amu
    -0.17
    POSITIVE LOGITS
    女æĢ§
    0.24
    -oriented
    0.21
    èķ´åIJ«
    0.20
    女è£ħ
    0.20
    ä¹ĭ声
    0.20
    çĶ·å¥³
    0.20
    åıįæĬĹ
    0.19
    çĶ·å£«
    0.19
    çĶ·æĢ§
    0.19
    -focused
    0.19
    Activations Density 0.031%

    No Known Activations