© 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. 278
    Prev
    Next
    INDEX
    Explanations

    panel

    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
    åļ¼
    -0.25
    sys
    -0.25
    :".
    -0.24
     chang
    -0.24
    /fast
    -0.23
    rai
    -0.23
    representation
    -0.23
    пов
    -0.23
     association
    -0.23
     midnight
    -0.23
    POSITIVE LOGITS
    lobs
    0.28
    çĿ¹
    0.25
    èĥ³
    0.25
    æľīéĴ±
    0.25
    icap
    0.24
     antiqu
    0.24
    InProgress
    0.24
    INUX
    0.24
     ins
    0.24
    ige
    0.24
    Activations Density 0.027%

    No Known Activations