© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17045
    Prev
    Next
    INDEX
    Explanations

    lactation, PET, PWM, radio, atom

    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
     Emb
    -0.21
    CRET
    -0.21
    è¿ŀäºij
    -0.20
    pite
    -0.20
    å¤ļéĩį
    -0.19
    ensch
    -0.19
    éĩįç»Ħ
    -0.19
     заÑĢегиÑģÑĤ
    -0.18
     Gef
    -0.18
    .itemView
    -0.18
    POSITIVE LOGITS
    Cla
    0.19
    Quarter
    0.18
    Formats
    0.18
     Cla
    0.18
     borough
    0.17
    åĵĶ
    0.17
    çĮ¾
    0.17
    abo
    0.17
    splice
    0.17
    igin
    0.17
    Activations Density 0.479%

    No Known Activations