© 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. 162501
    Prev
    Next
    INDEX
    Explanations

    a

    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
    _cpus
    -0.26
    å®ĺæĸ¹å¾®åįļ
    -0.25
    æĬ¥åijĬæľŁåĨħ
    -0.25
    é»į
    -0.25
    ogra
    -0.24
    oug
    -0.24
    oves
    -0.24
    ografia
    -0.23
    esti
    -0.23
    å·²ä¹ħçļĦ
    -0.23
    POSITIVE LOGITS
    erton
    0.28
     stub
    0.27
    ujet
    0.27
     Nay
    0.27
     hinted
    0.26
     Prompt
    0.26
    Jur
    0.25
    ç»Ń
    0.25
     Hod
    0.25
     mock
    0.24
    Activations Density 0.005%

    No Known Activations