© 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. 19-TRANSCODER-HP
    7. 7829
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    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
    пал
    -0.27
    SAM
    -0.27
    äºĶè¡Į
    -0.26
    Ĩµ
    -0.25
    (actions
    -0.25
     balance
    -0.25
    èIJ½
    -0.25
     valido
    -0.24
    åłĤ
    -0.24
    ol
    -0.24
    POSITIVE LOGITS
    NotFoundException
    0.28
    OKIE
    0.27
    pek
    0.27
     *</
    0.27
    ioc
    0.25
    ToInt
    0.25
    LIK
    0.25
    ÑĪек
    0.25
    ikon
    0.25
    ç£ķ
    0.24
    Activations Density 2.389%

    No Known Activations