© 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. 22410
    Prev
    Next
    INDEX
    Explanations

    cannabis and marijuana

    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
    Negative Logits
    eful
    -0.06
    ç³ĸæ°´
    -0.05
     Singer
    -0.05
    æĸ°ç¤¾
    -0.05
    endan
    -0.05
    anness
    -0.05
    EMB
    -0.05
    秩
    -0.05
     steward
    -0.05
    ç²ĺ
    -0.05
    POSITIVE LOGITS
    ipt
    0.06
    eus
    0.06
    ÑĢеÑģ
    0.06
    ee
    0.06
     cannabis
    0.06
    åĹħ
    0.05
     marijuana
    0.05
    çĪĨåıijçļĦ
    0.05
    ig
    0.05
     Cannabis
    0.05
    Activations Density 0.013%

    No Known Activations