© 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. 162538
    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
    eor
    -0.26
    å¼Ģå·¥
    -0.26
    CallCheck
    -0.25
    elize
    -0.25
    èĪį
    -0.24
     buildup
    -0.24
     plots
    -0.24
    åIJİåĨį
    -0.24
     cac
    -0.24
    åĮĸçļĦ
    -0.23
    POSITIVE LOGITS
    sters
    0.26
    -strip
    0.26
     Rule
    0.26
     Iso
    0.24
    éĵ¢
    0.24
    åĪĽæĸ°åŀĭ
    0.24
    STONE
    0.24
    è¶ħæłĩ
    0.24
    atform
    0.23
     Bukkit
    0.23
    Activations Density 0.011%

    No Known Activations