© 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
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 163451
    Prev
    Next
    INDEX
    Explanations

    Abbreviations/initialisms

    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
    enames
    -0.28
    ifacts
    -0.26
    ä¸ĢåĪĨéĴŁ
    -0.26
    ä¹ĭ举
    -0.24
    req
    -0.24
    .fixture
    -0.24
    Fix
    -0.24
     fixture
    -0.23
    _fix
    -0.23
    atz
    -0.23
    POSITIVE LOGITS
    çŃĶ辩
    0.27
     zd
    0.25
    éĢļç͍
    0.24
     professionally
    0.24
    èĮĥæĸĩ
    0.23
     Ord
    0.23
    è¿Ľåº¦
    0.23
     depos
    0.23
    èĥİåĦ¿
    0.23
     Proceed
    0.23
    Activations Density 0.005%

    No Known Activations