© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16905
    Prev
    Next
    INDEX
    Explanations

    what is / what does / what are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    å¹¶ä½ľ
    -0.08
    AGO
    -0.07
    é¦ĸåħĪåľ¨
    -0.07
    CAPE
    -0.07
    antuan
    -0.07
    elación
    -0.07
     pagr
    -0.07
    rastructure
    -0.06
    çĽĬ
    -0.06
    çļĨ为
    -0.06
    POSITIVE LOGITS
    r
    0.05
    za
    0.05
    ise
    0.05
    ness
    0.05
    ers
    0.05
    es
    0.05
     th
    0.05
    P
    0.05
    th
    0.05
    S
    0.05
    Activations Density 0.020%

    No Known Activations