© 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. 307
    Prev
    Next
    INDEX
    Explanations

    oc

    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
    mia
    -0.36
    tape
    -0.33
     tie
    -0.28
    ties
    -0.26
    便
    -0.26
    åĪ¶è£ģ
    -0.25
    #.
    -0.24
    ÄŁun
    -0.24
    å®ķ
    -0.24
    åIJĮæľŁ
    -0.23
    POSITIVE LOGITS
    Workbook
    0.28
    çĽĬ
    0.28
    agus
    0.28
    è½´æī¿
    0.25
    åĽ½åº¦
    0.25
    Show
    0.25
    $$$$
    0.24
    insic
    0.24
     fractional
    0.24
    太éĺ³
    0.23
    Activations Density 0.056%

    No Known Activations