© 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. 162901
    Prev
    Next
    INDEX
    Explanations

    varied topics

    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
    æĵį
    -0.28
    contro
    -0.28
     Georgetown
    -0.27
    è¿Ļåľº
    -0.27
     !_
    -0.26
    ptom
    -0.26
    "|
    -0.25
    "..
    -0.24
    orf
    -0.24
    å®īåİ¿
    -0.24
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.94
    æ¯Ķå¦Ĥ
    0.87
    å¦Ĥ
    0.81
     like
    0.73
    诸å¦Ĥ
    0.69
    æ¯Ķå¦Ĥ说
    0.69
    èѬå¦Ĥ
    0.64
    ä¾ĭãģĪãģ°
    0.60
     such
    0.57
     ÐĿапÑĢимеÑĢ
    0.56
    Activations Density 0.000%

    No Known Activations