© 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. 17009
    Prev
    Next
    INDEX
    Explanations

    pre- followed by other words

    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
    ãĤĪãģĨãģ«
    -0.18
    lah
    -0.16
    èĩªå¦Ĥ
    -0.16
    mel
    -0.16
    åīįéĢĶ
    -0.15
    --------------------------------------------------------------------------------
    -0.15
    uate
    -0.15
    sworth
    -0.15
    naire
    -0.15
    ullo
    -0.15
    POSITIVE LOGITS
    viously
    0.23
    bie
    0.22
    empt
    0.21
    nder
    0.21
    ponder
    0.21
    emption
    0.20
    ÑĪло
    0.20
    å®ļäºĨ
    0.19
    decess
    0.19
    Ùij
    0.18
    Activations Density 0.079%

    No Known Activations