© 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. 20372
    Prev
    Next
    INDEX
    Explanations

    densely situated parking thousand

    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
     bra
    -0.05
     f
    -0.05
     fr
    -0.05
     hun
    -0.05
     rass
    -0.05
    饵
    -0.05
    åĩ½
    -0.05
     tantal
    -0.05
    aranja
    -0.05
     Ø®Ùħ
    -0.05
    POSITIVE LOGITS
    追
    0.07
    ime
    0.06
    igo
    0.06
     Invocation
    0.06
    rick
    0.06
    以éĻį
    0.06
    iqu
    0.06
    à§į
    0.05
    çĻĴ
    0.05
    ien
    0.05
    Activations Density 0.004%

    No Known Activations