© 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. 17708
    Prev
    Next
    INDEX
    Explanations

    technical fields and topics

    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
     rem
    -0.06
     gr
    -0.05
    er
    -0.05
     us
    -0.05
     prof
    -0.05
    çļĦåħ³ç³»
    -0.05
     bid
    -0.05
     remote
    -0.05
     t
    -0.05
    槽
    -0.05
    POSITIVE LOGITS
    wed
    0.06
    cred
    0.06
    akaan
    0.06
    iked
    0.06
    失
    0.06
    crimin
    0.06
    edan
    0.06
    ité
    0.06
    失äºĨ
    0.06
    psy
    0.06
    Activations Density 0.092%

    No Known Activations