© 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. 96609
    Prev
    Next
    INDEX
    Explanations

    time

    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
    Frame
    -0.34
    _frame
    -0.28
     frame
    -0.28
    ç°§
    -0.27
    ewe
    -0.26
    isphere
    -0.26
    æŶåĢĻ
    -0.26
    MSN
    -0.26
    urga
    -0.25
    	frame
    -0.25
    POSITIVE LOGITS
     perception
    0.31
     itself
    0.29
    æĦŁçŁ¥
    0.28
     Perception
    0.28
     zones
    0.26
    å¾Ĺä½ı
    0.26
    ä»ĺ
    0.25
     sensed
    0.25
     perceived
    0.25
    çĽ£
    0.24
    Activations Density 0.887%

    No Known Activations