© 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. 161660
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    xCA
    -0.27
    decess
    -0.27
    oupper
    -0.26
    æľī人
    -0.26
     free
    -0.26
     themed
    -0.25
     simultaneous
    -0.25
    表éĿ¢ä¸Ĭ
    -0.25
    é¦ĸåħĪ
    -0.24
    ÑģÑĤвоваÑĤÑĮ
    -0.24
    POSITIVE LOGITS
    æĥij
    0.28
    mgr
    0.25
    æľ¬
    0.25
    ount
    0.24
    åİķ
    0.24
    æ¯ĶåĪ©
    0.24
    èĩªæ²»
    0.24
    ausible
    0.24
    äººæł¼
    0.23
    åħ¨æĹ¥
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.