© 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. 232
    Prev
    Next
    INDEX
    Explanations

    CSP

    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
    æĮ¨
    -0.27
    -insert
    -0.26
    icap
    -0.25
    ines
    -0.25
     bleed
    -0.23
     inserts
    -0.23
    procs
    -0.23
    ìłij
    -0.23
    åªĴ
    -0.23
     fullscreen
    -0.23
    POSITIVE LOGITS
    Beta
    0.27
    agna
    0.26
    setter
    0.24
    صÙĦا
    0.24
    éĩį
    0.24
    寶
    0.24
    éĨĴäºĨ
    0.24
     Beta
    0.24
    å®Ŀ
    0.23
    æĥ³
    0.23
    Activations Density 0.017%

    No Known Activations