© 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. 8943
    Prev
    Next
    INDEX
    Explanations

    expressing opinions

    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
    /repository
    -0.27
    lige
    -0.25
     manh
    -0.24
    ollect
    -0.24
    ç»Ħç»ĩçĶŁæ´»
    -0.23
    年第
    -0.23
     tess
    -0.23
    ANTE
    -0.23
    æ±ŁåĮĹ
    -0.23
     sourced
    -0.22
    POSITIVE LOGITS
    è¡£
    0.27
    =length
    0.26
    continent
    0.26
    æķ´ä¸ªäºº
    0.24
    (ed
    0.24
    åľŃ
    0.24
    èį¯
    0.24
     admitting
    0.24
    å°º
    0.23
    ×ķ׼×Ĺ
    0.23
    Activations Density 0.036%

    No Known Activations