© 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. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6653
    Prev
    Next
    INDEX
    Explanations

    Technical research

    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
    éļľç¢į
    -0.25
    dv
    -0.24
    åĴ¤
    -0.24
    éģ®
    -0.23
    ATAL
    -0.23
    .Modules
    -0.23
    routine
    -0.23
    ÑĪел
    -0.23
     Toll
    -0.23
    testdata
    -0.23
    POSITIVE LOGITS
    ây
    0.28
     flats
    0.27
    -linear
    0.26
    uely
    0.26
    åĨ»
    0.26
    Reviewed
    0.25
     Survival
    0.25
     survives
    0.25
     froze
    0.25
     survive
    0.24
    Activations Density 0.003%

    No Known Activations