© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19339
    Prev
    Next
    INDEX
    Explanations

    to followed by verb

    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
    azzo
    -0.08
     consecu
    -0.08
    iert
    -0.07
    .sav
    -0.07
    eel
    -0.07
    erenza
    -0.07
    blia
    -0.07
    gles
    -0.07
    leur
    -0.07
    hero
    -0.07
    POSITIVE LOGITS
    s
    0.05
    å½ĵçĦ¶äºĨ
    0.05
    оÑĢо
    0.05
    è¿Ļæł·çļĦ
    0.05
    åĪ°
    0.05
     revers
    0.05
    ìĿ´
    0.05
    H
    0.04
    å¾Ĺè¿ĩ
    0.04
     measurable
    0.04
    Activations Density 0.001%

    No Known Activations