© 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. 7090
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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
    æŁIJ个
    -0.27
    croft
    -0.25
    çĭ¬ç«ĭ
    -0.24
    æŁIJ
    -0.24
    kes
    -0.24
    à¹ģà¸Ļ
    -0.23
    çĶ«
    -0.23
    æľŁåĨħ
    -0.23
    æŀļ
    -0.23
    游
    -0.23
    POSITIVE LOGITS
    uin
    0.28
    ould
    0.27
    ש×Ķ
    0.26
     tagged
    0.26
    JI
    0.25
    typed
    0.24
     precedence
    0.24
    æĵĤ
    0.24
     SVN
    0.23
    æģ¶åĮĸ
    0.23
    Activations Density 0.035%

    No Known Activations