© 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. 22368
    Prev
    Next
    INDEX
    Explanations

    anal play. anal play. anal play

    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
    reb
    -0.07
    oa
    -0.07
    ç©¿è¡Į
    -0.06
     adem
    -0.06
    .issue
    -0.06
     costing
    -0.06
    ç«ĻåĪ°
    -0.06
     Zoals
    -0.06
    Site
    -0.06
     RaycastHit
    -0.06
    POSITIVE LOGITS
    è¿ĩ大
    0.06
    åħ·
    0.06
    åŁ¹èĤ²
    0.05
    åŁ¹
    0.05
    eware
    0.05
    åŁ¹åħ»
    0.05
    èī¯
    0.05
    çĶ¨
    0.04
    anger
    0.04
     larger
    0.04
    Activations Density 0.004%

    No Known Activations