© 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. 148
    Prev
    Next
    INDEX
    Explanations

    h

    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
    @a
    -0.27
    otel
    -0.26
     Honor
    -0.25
    è¶ħé¢Ŀ
    -0.24
    åįĩ
    -0.24
    =edge
    -0.24
    =root
    -0.24
    è¿ĩé«ĺ
    -0.24
    笫
    -0.24
    /stat
    -0.23
    POSITIVE LOGITS
    nowled
    0.26
    feit
    0.26
     Forge
    0.26
    osomal
    0.25
     turnout
    0.25
    Å©ng
    0.25
    éĺļ
    0.25
     Prediction
    0.25
    _mapper
    0.25
    تÙħر
    0.24
    Activations Density 0.011%

    No Known Activations