© 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. 11781
    Prev
    Next
    INDEX
    Explanations

    processing unit

    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
     sourceMapping
    -0.22
    rear
    -0.20
    æįº
    -0.19
    füg
    -0.19
    olin
    -0.19
    icorn
    -0.18
    alom
    -0.18
    åģĮ
    -0.18
    ç¡ĸ
    -0.18
    èĢģ人家
    -0.18
    POSITIVE LOGITS
    çĶ«
    0.22
     Grass
    0.21
    èįī
    0.21
    nit
    0.20
    ยà¸Ńà¸Ķ
    0.19
    éħį
    0.19
     grass
    0.19
    åĿļæŀľ
    0.18
    ç»Ħ
    0.18
    marshal
    0.18
    Activations Density 0.293%

    No Known Activations