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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89202
    Prev
    Next
    INDEX
    Explanations

    Code and math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _GU
    -0.26
    éľĢè¦ģçĶ¨åĪ°
    -0.25
     ÑħоÑĤиÑĤе
    -0.24
    çħŀ
    -0.24
     motive
    -0.24
     Vice
    -0.23
    è¦ĥ
    -0.23
    çģµæĦŁ
    -0.23
     pand
    -0.23
    å¦Ĭ
    -0.22
    POSITIVE LOGITS
    å°ļ
    0.28
    ãģĤãģ£ãģ¦
    0.27
    çļĦéĩįè¦ģæĢ§
    0.26
    _view
    0.26
    aron
    0.26
    çĴ§
    0.26
    æľŁè´§
    0.26
     lap
    0.26
     reim
    0.25
    +N
    0.25
    Activations Density 10.012%

    No Known Activations