© 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. 162325
    Prev
    Next
    INDEX
    Explanations

    Connecticut

    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
    çĭ±
    -0.30
    hausen
    -0.29
    çįĦ
    -0.27
    mscorlib
    -0.25
     aide
    -0.25
    éľĩ
    -0.24
    _TUN
    -0.24
    aid
    -0.24
    ipse
    -0.24
    ski
    -0.24
    POSITIVE LOGITS
    è¯Ń
    0.26
     Pot
    0.25
     HI
    0.25
    æµĭ
    0.24
    åı¦ä¸Ģ
    0.24
    伶
    0.24
    ç§ī
    0.23
    è¿ĽåĮĸ
    0.23
     sequ
    0.23
     linea
    0.23
    Activations Density 0.031%

    No Known Activations