© 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. 16886
    Prev
    Next
    INDEX
    Explanations

    having same names

    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
     nominal
    -0.05
     null
    -0.05
     Nom
    -0.05
    oblig
    -0.05
    -0.05
     D
    -0.05
     further
    -0.05
    çĬ¹
    -0.05
     oblig
    -0.04
     (
    -0.04
    POSITIVE LOGITS
    uco
    0.08
    éĥ½æĺ¯ä¸ĢäºĽ
    0.07
    arial
    0.07
    'user
    0.07
    turned
    0.06
     Maire
    0.06
     Anforder
    0.06
    oure
    0.06
     dure
    0.06
     Ehren
    0.06
    Activations Density 0.002%

    No Known Activations