© 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. 4764
    Prev
    Next
    INDEX
    Explanations

    Comma

    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
     AppState
    -0.27
    åªĴä½ĵæĬ¥éģĵ
    -0.26
    AppState
    -0.26
    gu
    -0.25
    çĭĢ
    -0.25
    åĽŀ头
    -0.24
    _MEMORY
    -0.24
    æİ¥éĢģ
    -0.24
    .Mutable
    -0.24
    åĨ¶
    -0.23
    POSITIVE LOGITS
    ramid
    0.28
    licas
    0.27
    ddie
    0.27
    olland
    0.27
    stry
    0.26
    quot
    0.26
     воÑĤ
    0.26
     lot
    0.25
     forty
    0.25
    ót
    0.24
    Activations Density 0.011%

    No Known Activations