© 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. 88700
    Prev
    Next
    INDEX
    Explanations

    coherent english phrases

    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
    å°±è¿ŀ
    -0.28
     RequestOptions
    -0.26
     feelings
    -0.26
    æĢĻ
    -0.26
    azen
    -0.26
    lox
    -0.26
    erver
    -0.26
    çī¹èī²äº§ä¸ļ
    -0.26
    éĦ±
    -0.25
    å¸Ĥåľºç»ıæµİ
    -0.25
    POSITIVE LOGITS
    åIJįä¹ī
    0.28
     diffuse
    0.26
     remain
    0.25
    ocular
    0.24
     remains
    0.24
    kg
    0.23
    á»ģ
    0.23
     ÑĤогда
    0.23
    ä¹ĭäºī
    0.23
    olu
    0.23
    Activations Density 33.715%

    No Known Activations