© 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. 163324
    Prev
    Next
    INDEX
    Explanations

    THE

    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
    against
    -0.30
    ensen
    -0.28
    _gradients
    -0.26
    åĽŀ头çľĭ
    -0.25
    顽
    -0.25
    ighting
    -0.25
    ashes
    -0.25
    adult
    -0.24
    azel
    -0.24
     NXT
    -0.24
    POSITIVE LOGITS
    IT
    0.27
    bez
    0.27
     pertinent
    0.27
    æľīå¤ļ大
    0.26
     Fall
    0.26
     dÃ¼ÅŁ
    0.25
     dut
    0.25
    relevant
    0.25
    åijĬ
    0.25
     relevant
    0.24
    Activations Density 0.040%

    No Known Activations