© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129976
    Prev
    Next
    INDEX
    Explanations

    formal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åij¼åĴĮ
    -0.27
    ä¸Ģæł·çļĦ
    -0.26
    Storm
    -0.25
    çļĦåij½è¿IJ
    -0.25
     Cascade
    -0.25
    ä¸į平衡
    -0.25
    åĪ«äººçļĦ
    -0.24
     uÄŁra
    -0.24
    æ»ĺ
    -0.24
    éĺį
    -0.24
    POSITIVE LOGITS
    essian
    0.25
    avn
    0.25
     choice
    0.24
     Mein
    0.24
    ationale
    0.24
    htar
    0.24
     HttpResponseMessage
    0.24
    .rdf
    0.23
     toJSON
    0.23
    _PREF
    0.23
    Activations Density 0.008%

    No Known Activations