© 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. 162425
    Prev
    Next
    INDEX
    Explanations

    Op

    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
    =edge
    -0.28
    说å®ŀ
    -0.27
    çijķ
    -0.27
    ä¸Ńåħ³
    -0.26
    otec
    -0.26
     Ment
    -0.26
    æīĢ以说
    -0.25
     vign
    -0.25
    akening
    -0.25
    iske
    -0.24
    POSITIVE LOGITS
    èĩŃ
    0.37
    é¼»
    0.31
    å±ģèĤ¡
    0.31
    åħ«åį¦
    0.31
    裤
    0.29
    è´Ńçī©
    0.28
    åı£æ°´
    0.28
    çŀª
    0.28
    å±ģ
    0.27
    ï¼Īç¬ij
    0.27
    Activations Density 0.009%

    No Known Activations