© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22165
    Prev
    Next
    INDEX
    Explanations

    porphyrins, piperidinyl, naphthyl, styryl

    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
    /AFP
    -0.06
    auff
    -0.05
    鬱
    -0.05
    åħļç»Ħ
    -0.05
    zimmer
    -0.05
    typescript
    -0.05
    pressione
    -0.05
     vigil
    -0.05
    éĸī
    -0.05
     ith
    -0.05
    POSITIVE LOGITS
    åĪĽå»ºäºİ
    0.06
    ctic
    0.06
    èµ´ç¾İ
    0.06
    让èĩªå·±çļĦ
    0.06
    丽人
    0.06
    _Word
    0.06
    ÙĦÙģ
    0.06
    ìĸ´ë¡ľ
    0.06
    é£ĵ
    0.05
    onden
    0.05
    Activations Density 0.005%

    No Known Activations