© 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. 162621
    Prev
    Next
    INDEX
    Explanations

    (

    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
     f
    -0.30
     нев
    -0.28
     append
    -0.28
     chant
    -0.28
     list
    -0.27
     embedded
    -0.26
     u
    -0.26
     welfare
    -0.25
     langs
    -0.25
    izen
    -0.24
    POSITIVE LOGITS
    éĹº
    0.29
    å¾®
    0.27
    lord
    0.26
    lements
    0.25
    .Fl
    0.25
    头顶
    0.24
    arme
    0.24
    aise
    0.24
    Fl
    0.24
    spring
    0.23
    Activations Density 0.024%

    No Known Activations