© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161734
    Prev
    Next
    INDEX
    Explanations

    code or math

    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
     instead
    -1.04
    åıįèĢĮ
    -1.03
    èĢĮä¸įæĺ¯
    -1.01
     rather
    -0.99
    instead
    -0.89
    rather
    -0.87
     Instead
    -0.86
    èĢĮéĿŀ
    -0.85
     Rather
    -0.82
     ìĺ¤íŀĪ볤
    -0.81
    POSITIVE LOGITS
    ufe
    0.26
    allee
    0.26
    uf
    0.25
    ufs
    0.25
    æłijèĦĤ
    0.24
    JNI
    0.24
    ein
    0.24
    amburg
    0.24
    åªĴ
    0.24
    æĭŁ
    0.23
    Activations Density 0.007%

    No Known Activations