© 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. 11785
    Prev
    Next
    INDEX
    Explanations

    accelerator collider beam electron millisecond

    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
    èĥİ
    -0.19
    \common
    -0.18
     DropIndex
    -0.18
    ilik
    -0.18
    æİīèIJ½
    -0.18
    è§Ĥ念
    -0.18
    alink
    -0.18
    åĻ¤
    -0.18
    ewise
    -0.18
    TECT
    -0.18
    POSITIVE LOGITS
    æ¿Ģ
    0.27
    rays
    0.22
    mill
    0.22
    èģļçĦ¦
    0.22
     rail
    0.22
    pulse
    0.20
     milliseconds
    0.20
    大åŀĭ
    0.20
    çĶŁæĪIJ
    0.20
    å°Ħ
    0.20
    Activations Density 0.112%

    No Known Activations