© 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. 330
    Prev
    Next
    INDEX
    Explanations

    ase

    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
    ansi
    -0.29
    orne
    -0.29
    iet
    -0.24
    modulo
    -0.24
    ç«ŀäºīä¼ĺåĬ¿
    -0.23
    èµĸ
    -0.23
    æ·ĸ
    -0.23
     kto
    -0.23
    arella
    -0.23
    /styles
    -0.23
    POSITIVE LOGITS
    çİĦ
    0.31
    åĺ´
    0.30
     operand
    0.26
    zelf
    0.25
    Away
    0.25
    yum
    0.24
    éĵī
    0.24
     Kob
    0.24
    å¼ĢéĢļ
    0.23
     Need
    0.23
    Activations Density 0.014%

    No Known Activations