© 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. 21285
    Prev
    Next
    INDEX
    Explanations

    poisoning and poisons

    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
    еÑģÑĮ
    -0.06
    orb
    -0.06
    wes
    -0.06
    eah
    -0.06
    reme
    -0.05
    vang
    -0.05
    orent
    -0.05
    ç´¢æĢ§
    -0.05
     turbulence
    -0.05
     Reynolds
    -0.05
    POSITIVE LOGITS
    fas
    0.07
    åIJĪåIJĮæŶ
    0.06
    AFP
    0.06
    ç½¢
    0.06
    Austr
    0.06
     жало
    0.06
    fos
    0.06
     aposent
    0.06
    ЩÐĺ
    0.05
    oyer
    0.05
    Activations Density 0.010%

    No Known Activations