© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 306
    Prev
    Next
    INDEX
    Explanations

    Frederick and derivations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹Ķ
    -0.26
    -ground
    -0.25
    ä¹ŁæĹłæ³ķ
    -0.25
    éĩįè¦ģ讲è¯Ŀ
    -0.24
     Heath
    -0.24
     say
    -0.23
    :');↵
    -0.23
    ...',↵
    -0.23
    Hamilton
    -0.23
     Trident
    -0.22
    POSITIVE LOGITS
    ish
    0.25
    lei
    0.24
    -bin
    0.24
     Decoration
    0.24
    ange
    0.24
    åĨħç½®
    0.24
    æµģåĩº
    0.23
    zas
    0.23
     (()
    0.23
    ä¸Ģ级
    0.23
    Activations Density 0.011%

    No Known Activations