© 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. 163299
    Prev
    Next
    INDEX
    Explanations

    called

    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
    @a
    -0.26
    åĬ©æݨ
    -0.25
     esl
    -0.24
    äºĨä»ĸçļĦ
    -0.24
    olio
    -0.24
    çıŀ
    -0.24
    __[
    -0.23
    åĮĸ
    -0.23
    veral
    -0.23
     Melania
    -0.23
    POSITIVE LOGITS
     “
    0.60
     "
    0.55
     ‘
    0.47
    “
    0.43
     '
    0.43
     âĢŀ
    0.42
     ”
    0.41
     "<
    0.38
     ``
    0.38
     «
    0.35
    Activations Density 0.111%

    No Known Activations