© 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. 7685
    Prev
    Next
    INDEX
    Explanations

    Size and degree

    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
     ActionType
    -0.28
    enty
    -0.27
    .addAction
    -0.27
    ä¸ĭåİ»
    -0.27
     createAction
    -0.26
    æĮĩçĶ²
    -0.25
    aaS
    -0.25
     Reflex
    -0.24
    à¸Ľà¸£à¸²
    -0.23
     Continental
    -0.23
    POSITIVE LOGITS
    .GetResponse
    0.26
     brace
    0.26
    å®Ī
    0.25
    åĩĨå¤ĩ
    0.24
     Bour
    0.24
    åıŁ
    0.24
    ogl
    0.24
     prepar
    0.24
    Vict
    0.23
    llu
    0.23
    Activations Density 0.022%

    No Known Activations