© 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. 21653
    Prev
    Next
    INDEX
    Explanations

    inputting, injecting, or passing through

    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
    cket
    -0.06
    icola
    -0.06
     clin
    -0.06
    :?
    -0.06
     reloc
    -0.06
    اÙĨس
    -0.06
    eby
    -0.06
    orb
    -0.06
    çĮľåĪ°
    -0.06
     favour
    -0.06
    POSITIVE LOGITS
    aray
    0.05
     subjected
    0.05
    éĺħ
    0.05
    å¤Ħäºİ
    0.05
    讯
    0.05
     Gateway
    0.05
    已达åĪ°
    0.05
    äººæľº
    0.05
     Kurz
    0.05
     processing
    0.05
    Activations Density 0.021%

    No Known Activations