© 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. 21911
    Prev
    Next
    INDEX
    Explanations

    make followed by specific words

    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
    écur
    -0.07
    åĬ¡
    -0.06
    ihak
    -0.06
    ify
    -0.06
    åĪ»
    -0.06
    itizen
    -0.06
    ward
    -0.06
    ondon
    -0.05
    Цен
    -0.05
    æ¯Ķäºļ
    -0.05
    POSITIVE LOGITS
    ed
    0.07
    develop
    0.06
     Fah
    0.05
    oord
    0.05
    antry
    0.05
    enido
    0.05
    çĶ³è¯·æī§è¡Į
    0.05
    æľŁåĨħ
    0.05
    ãĥ³
    0.05
    amac
    0.05
    Activations Density 0.009%

    No Known Activations