© 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. 288
    Prev
    Next
    INDEX
    Explanations

    suppress

    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
    人æ°ij
    -0.30
    arrays
    -0.28
     Vect
    -0.27
    .consume
    -0.26
    åij½è¿IJ
    -0.26
    Exchange
    -0.25
    æ°ijä¼Ĺ
    -0.25
     Instruction
    -0.24
    _ATTRIBUTE
    -0.24
    çĻ¾å§ĵ
    -0.24
    POSITIVE LOGITS
     restraint
    0.28
    hest
    0.28
    xies
    0.27
     mastur
    0.26
    itory
    0.25
    åĿ¦
    0.25
    erah
    0.25
     distilled
    0.25
    ees
    0.24
    antino
    0.24
    Activations Density 0.028%

    No Known Activations