© 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. 7240
    Prev
    Next
    INDEX
    Explanations

    individual

    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
    kerja
    -0.26
     backgroundImage
    -0.25
    platz
    -0.25
    ndata
    -0.25
    åĩºåľŁ
    -0.24
    æ»ŀåIJİ
    -0.24
    è·¨åĽ½
    -0.24
    级以ä¸Ĭ
    -0.23
    转移
    -0.23
    èģĶåIJĪä¼ļ
    -0.23
    POSITIVE LOGITS
     matière
    0.31
     matters
    0.27
    èݼ
    0.26
    åĵĹ
    0.26
    chai
    0.26
    ocks
    0.23
    -prop
    0.23
     dr
    0.23
     ev
    0.23
    á»ıi
    0.23
    Activations Density 0.016%

    No Known Activations