© 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. 89211
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific writing

    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
     compare
    -0.44
     originals
    -0.41
    æŃ£å¸¸
    -0.41
     compar
    -0.41
    对çħ§
    -0.40
     compares
    -0.40
    æŃ£å¸¸çļĦ
    -0.39
    compare
    -0.38
    缸æ¯Ķ
    -0.37
    对æ¯Ķ
    -0.37
    POSITIVE LOGITS
     internally
    0.28
    à¹ģห
    0.27
    éĽĨä¸Ń
    0.25
     Concent
    0.25
     NOI
    0.25
    缸åħ³åĨħ容
    0.24
    ä¸ŃéĢĶ
    0.23
    åĨħåľ¨
    0.23
    å²Ļ
    0.23
    enga
    0.23
    Activations Density 47.577%

    No Known Activations