© 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. 162468
    Prev
    Next
    INDEX
    Explanations

    Organizations names

    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
     except
    -0.27
     serving
    -0.26
     apart
    -0.25
     facing
    -0.25
     contract
    -0.24
    orges
    -0.24
     pari
    -0.24
    èįij
    -0.24
     contracts
    -0.24
    :view
    -0.24
    POSITIVE LOGITS
    Head
    0.30
    /A
    0.30
      ↵
    0.30
    /
    0.29
     /
    0.28
    عÙħ
    0.28
    Phase
    0.28
    è·ĥ
    0.27
     refer
    0.26
    å¯ĨåĪĩ
    0.26
    Activations Density 0.014%

    No Known Activations