© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15098
    Prev
    Next
    INDEX
    Explanations

    bulk modifiers

    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
    ãĥ³ãĤ°
    -0.18
    รา
    -0.18
    åħ¶æīĢ
    -0.16
    ials
    -0.16
    .locals
    -0.16
     ÅŁek
    -0.15
     slightest
    -0.15
    ements
    -0.15
    ecz
    -0.15
    iable
    -0.15
    POSITIVE LOGITS
    mates
    0.26
    ify
    0.24
    ified
    0.22
    ier
    0.22
    ers
    0.21
    aroo
    0.21
    mate
    0.21
    iness
    0.19
    buster
    0.19
    edImage
    0.19
    Activations Density 0.007%

    No Known Activations