© 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. 22341
    Prev
    Next
    INDEX
    Explanations

    mechanical

    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
    ова
    -0.06
    -
    -0.06
    Âł
    -0.05
    -0.05
    TH
    -0.05
    åĪĨæķ£
    -0.05
    çĬģ
    -0.05
    åŃĶ
    -0.05
    ä¸ĵ注
    -0.05
    åľŁæľ¨
    -0.05
    POSITIVE LOGITS
    åī¯å¤Ħéķ¿
    0.08
    hic
    0.07
    æݨæķ²
    0.06
    ä¸Ĭä¸Ģ次
    0.06
    ä¿¡è¾¾
    0.06
    ÙĤاط
    0.06
    irection
    0.06
    менÑıÑĤÑĮ
    0.06
     kend
    0.06
    两头
    0.06
    Activations Density 0.002%

    No Known Activations