© 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
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 95391
    Prev
    Next
    INDEX
    Explanations

    duration

    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
    chio
    -0.27
    agn
    -0.26
    ä¼ı
    -0.25
    æľ½
    -0.25
    æ°¸
    -0.24
    æ°¸ä¹ħ
    -0.24
    иÑģк
    -0.24
    /Gate
    -0.24
    常年
    -0.24
    eous
    -0.24
    POSITIVE LOGITS
     of
    0.43
    -of
    0.42
    _of
    0.39
     Of
    0.36
    Of
    0.35
    _OF
    0.34
    OfClass
    0.33
    OfFile
    0.32
    	of
    0.32
    .of
    0.30
    Activations Density 0.011%

    No Known Activations