© 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. 22340
    Prev
    Next
    INDEX
    Explanations

    setting data pointer

    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
    s
    -0.05
     Methodist
    -0.05
     cor
    -0.05
    Sharp
    -0.05
    lette
    -0.05
     Hal
    -0.05
     thought
    -0.05
     Tew
    -0.05
     Sharp
    -0.05
    åѦ
    -0.05
    POSITIVE LOGITS
    çĥ¨
    0.07
    нÑıÑĤие
    0.07
    çģĺ
    0.06
    ÑĪли
    0.06
    ØŃÙĪ
    0.06
    entas
    0.06
    acl
    0.06
    åŀ
    0.06
    tig
    0.06
    æ¼ĶæĦĪ
    0.06
    Activations Density 0.040%

    No Known Activations