© 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. 162592
    Prev
    Next
    INDEX
    Explanations

    statistics

    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
    ORY
    -0.27
    tü
    -0.26
     Happiness
    -0.26
    oire
    -0.25
     Weather
    -0.25
     Äijáng
    -0.25
    cold
    -0.24
    ä¸Ģæŀ¶
    -0.24
     UIControl
    -0.24
    -Year
    -0.24
    POSITIVE LOGITS
     kron
    0.26
    çĤ¼
    0.24
    ENSIONS
    0.24
     Kron
    0.24
    xac
    0.24
    亿
    0.23
     outpatient
    0.23
    åĴĮå®ĮåĸĦ
    0.23
    asure
    0.23
    inka
    0.23
    Activations Density 0.009%

    No Known Activations