© 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. 30-TRANSCODER-HP
    7. 96610
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     patch
    -0.30
    ercul
    -0.27
     pul
    -0.27
     ret
    -0.27
     discontin
    -0.26
    illary
    -0.26
    æİ£
    -0.26
    jah
    -0.25
    æ´¾
    -0.25
    atan
    -0.24
    POSITIVE LOGITS
    åĺ¤
    0.30
    éķ¿éķ¿
    0.26
    otted
    0.26
    Lambda
    0.25
    editor
    0.25
    æ¹ĸåĮº
    0.25
    _throw
    0.24
    并åIJij
    0.24
     defense
    0.23
    åı¤äºº
    0.23
    Activations Density 0.896%

    No Known Activations