© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163386
    Prev
    Next
    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     independently
    -0.31
    STA
    -0.28
    åĩº
    -0.27
     engaged
    -0.26
     Nokia
    -0.25
    \Factory
    -0.24
    ym
    -0.24
     dr
    -0.24
     div
    -0.24
    çĭ¬ç«ĭ
    -0.24
    POSITIVE LOGITS
    çĶŁäº§åĬĽ
    0.30
    以ä¸ĬçļĦ
    0.30
    åĩłä½į
    0.29
    å¿ĥä¸ŃçļĦ
    0.29
    å²Į
    0.28
    产èĥ½
    0.27
    åĬĽè¿ĺæĺ¯
    0.27
    åĮĹ大
    0.27
    å¿ĥ缮
    0.27
    éĤ£äºĽ
    0.26
    Activations Density 0.011%

    No Known Activations