© 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. 11269
    Prev
    Next
    INDEX
    Explanations

    word separators

    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
    opp
    -0.20
     cross
    -0.20
    Wh
    -0.19
    ç¢į
    -0.19
    apt
    -0.18
    Wnd
    -0.18
    سÙĥ
    -0.18
    clus
    -0.17
     Rolling
    -0.17
    /***/
    -0.17
    POSITIVE LOGITS
    å´©
    0.23
    å¤ĩ注
    0.21
    åħ¶å®ĥ
    0.21
    åħ¶ä»ĸçļĦ
    0.20
    ngth
    0.20
    åĢĻ
    0.20
    FilterWhere
    0.19
    以åıĬåħ¶ä»ĸ
    0.19
    常年
    0.19
    åij¨è¾¹
    0.19
    Activations Density 0.111%

    No Known Activations