© 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. 6429
    Prev
    Next
    INDEX
    Explanations

    War and code

    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
     *</
    -0.27
    åĩĨåħ¥
    -0.25
    çIJĨäºĭä¼ļ
    -0.25
    çļĦäºĭå®ŀ
    -0.24
    é³ı
    -0.24
     koÅĽci
    -0.24
     (*
    -0.23
    alternate
    -0.23
    ADATA
    -0.23
    ah
    -0.23
    POSITIVE LOGITS
    ستاÙĨ
    0.26
    转载请
    0.25
     Loved
    0.24
    laps
    0.24
     repl
    0.24
    _RS
    0.23
    ophilia
    0.23
    owler
    0.23
    æ¾İæ¹ĥæĸ°éĹ»
    0.23
    èħ¥
    0.23
    Activations Density 0.003%

    No Known Activations