© 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. 96194
    Prev
    Next
    INDEX
    Explanations

    opt

    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
     good
    -0.32
    èī¯å¥½
    -0.28
    好çļĦ
    -0.28
    好åIJ§
    -0.28
    complexType
    -0.28
     GOOD
    -0.27
    YTE
    -0.27
    good
    -0.27
    appy
    -0.26
    GOOD
    -0.26
    POSITIVE LOGITS
     for
    0.52
    ForKey
    0.42
    for
    0.40
    For
    0.39
     For
    0.36
    _for
    0.36
     für
    0.36
    _For
    0.35
    ForResource
    0.34
    ä½Ĩæĺ¯å¯¹äºİ
    0.33
    Activations Density 0.001%

    No Known Activations