© 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. 16182
    Prev
    Next
    INDEX
    Explanations

    names starting with Ke

    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
    sWith
    -0.23
    ination
    -0.18
    screen
    -0.16
    sd
    -0.16
    ree
    -0.16
    mates
    -0.16
    swagen
    -0.16
    sp
    -0.15
    sn
    -0.15
    eurs
    -0.15
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.26
    å·²ä¹ħçļĦ
    0.17
    ystone
    0.16
    é¹ĺ
    0.16
    OTES
    0.15
    emos
    0.15
    brace
    0.15
    ãģĵãģ¨ãģĮãģ§ãģį
    0.15
    ode
    0.14
    åīįæīĢ
    0.14
    Activations Density 0.015%

    No Known Activations