© 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. 162289
    Prev
    Next
    INDEX
    Explanations

    Numbers and dates

    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
    ñ
    -0.28
    enis
    -0.27
    oho
    -0.26
    .fn
    -0.26
    åķĥ
    -0.25
    åĨį
    -0.25
    åĪĩ
    -0.25
    使
    -0.24
    {}.
    -0.24
    åĩŃ
    -0.24
    POSITIVE LOGITS
    æĦł
    0.28
    åģ¥
    0.27
    emento
    0.25
     Connections
    0.25
    è¿Ļç§įäºĭæĥħ
    0.24
    igion
    0.24
    éĿĻéĿĻ
    0.24
     hè
    0.24
    ë°
    0.24
     dams
    0.24
    Activations Density 0.004%

    No Known Activations