© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5114
    Prev
    Next
    INDEX
    Explanations

    equivalence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agos
    -0.28
    éro
    -0.27
    ç¢İçīĩ
    -0.27
    æĭ¾
    -0.27
    illo
    -0.26
    ÅĤó
    -0.26
    èħIJ
    -0.26
    èĻ½çĦ¶
    -0.25
    ä»ĸ认为
    -0.25
    åĨĹ
    -0.24
    POSITIVE LOGITS
    å¢ĥ
    0.29
     combining
    0.24
    称
    0.24
    ',)↵
    0.24
    enton
    0.24
     Seeking
    0.24
    éħ¿éħĴ
    0.24
     gathers
    0.24
     general
    0.23
    ZY
    0.23
    Activations Density 0.007%

    No Known Activations