© 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. 6
    Prev
    Next
    INDEX
    Explanations

    evil

    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
     cầm
    -0.31
    	ev
    -0.26
    SHOT
    -0.26
    ev
    -0.25
    å®ĮæĪIJ
    -0.24
    -origin
    -0.24
    åIJĦ
    -0.23
    ä¼Ĭ
    -0.23
    arity
    -0.23
    rina
    -0.23
    POSITIVE LOGITS
     populated
    0.26
     powerless
    0.26
    ல
    0.25
    寨
    0.25
    acman
    0.24
     unveil
    0.24
    å²Ļ
    0.24
     hugs
    0.24
    æŶæŶ
    0.24
    locker
    0.24
    Activations Density 0.044%

    No Known Activations