© 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. 9296
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific contexts

    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
    ÐIJÐŀ
    -0.29
    çĨŁ
    -0.28
    SM
    -0.28
    ny
    -0.26
    å¼Ģåĩº
    -0.25
    åĴĮ个人
    -0.25
    BJ
    -0.25
     latter
    -0.25
     overd
    -0.25
     given
    -0.25
    POSITIVE LOGITS
    è¦ģåİ»
    0.26
     Redistributions
    0.25
    è¾ķ
    0.25
     frontal
    0.25
    oris
    0.24
    /cache
    0.24
    itionally
    0.24
    åĬĽè¿ĺæĺ¯
    0.24
    ubre
    0.24
    beros
    0.23
    Activations Density 0.015%

    No Known Activations