© 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. 8035
    Prev
    Next
    INDEX
    Explanations

    problems, questions, personal struggles

    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
    ä¸Ģç»ı
    -0.25
    .camel
    -0.25
     Kenn
    -0.25
    TN
    -0.25
    yled
    -0.24
    неÑģен
    -0.23
    arget
    -0.23
    +","+
    -0.23
     disb
    -0.23
     subscribed
    -0.23
    POSITIVE LOGITS
    æĹłåĬĽ
    0.39
     insufficient
    0.36
    æĹłæ³ķ
    0.34
     struggles
    0.33
    说ä¸įåĩº
    0.33
     inability
    0.33
    缺å°ij
    0.33
    éļ¾ä»¥
    0.33
    æľªèĥ½
    0.32
     incomplete
    0.31
    Activations Density 0.066%

    No Known Activations