Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 163627
    Prev
    Next
    INDEX
    Explanations

    Descriptions, explanations, instructions

    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
    union
    -0.26
    è¯ľ
    -0.26
    raph
    -0.26
    ierten
    -0.25
    bens
    -0.24
    RAY
    -0.24
    .tools
    -0.24
    upy
    -0.24
     union
    -0.23
    鼷
    -0.23
    POSITIVE LOGITS
    :
    0.41
    å¦Ĥä¸ĭ
    0.29
    :↵
    0.29
     following
    0.29
    :↵↵
    0.28
     follows
    0.28
    ï¼ļ
    0.27
    :\
    0.27
    following
    0.27
     seguint
    0.27
    Activations Density 0.007%

    No Known Activations