© 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
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 163340
    Prev
    Next
    INDEX
    Explanations

    android

    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
    éķ¿å¤§
    -0.29
    ä¸Ģ家人
    -0.27
    ä¸Ģæīĭ
    -0.26
    åħį责声æĺİ
    -0.26
    æĥº
    -0.25
    ses
    -0.25
     specificity
    -0.24
    ancies
    -0.24
    ãĤ±ãĥĥãĥĪ
    -0.24
     brides
    -0.24
    POSITIVE LOGITS
    ä»»ä½ķæĹ¶åĢĻ
    0.27
    acular
    0.27
    aller
    0.26
    .setLayout
    0.25
    æŃ»
    0.25
    纣
    0.25
    odable
    0.24
    imore
    0.24
    oe
    0.23
    颤
    0.23
    Activations Density 0.134%

    No Known Activations