© 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. 13673
    Prev
    Next
    INDEX
    Explanations

    is followed by sequence, Args, Override, or isolation

    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
    åİ®
    -0.19
    gether
    -0.19
    /from
    -0.18
    llx
    -0.17
    yled
    -0.16
     fkk
    -0.16
    ils
    -0.15
    ofile
    -0.15
    ILLS
    -0.15
    stants
    -0.15
    POSITIVE LOGITS
    olation
    0.26
    olate
    0.26
    olated
    0.24
    åīįæīĢ
    0.24
    ÙĬØ©
    0.21
    otropic
    0.21
    abelle
    0.21
    abella
    0.20
    æĢ§åĴĮ
    0.20
    å®ļäºĨ
    0.19
    Activations Density 0.115%

    No Known Activations