© 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. 24-TRANSCODER-HP
    7. 149645
    Prev
    Next
    INDEX
    Explanations

    economy and money

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contempor
    -0.30
    è¾¹éĻħ
    -0.28
     disag
    -0.27
     headline
    -0.25
    Coord
    -0.24
     VAR
    -0.24
    bone
    -0.24
    代çIJĨ人
    -0.24
     programme
    -0.24
    å¼Ĥ
    -0.24
    POSITIVE LOGITS
    åħ¨çIJĥç»ıæµİ
    0.31
    ç»ıæµİæķĪçĽĬ
    0.27
    å¸Ĥåľºç»ıæµİ
    0.26
     scop
    0.26
     economical
    0.26
    ENTS
    0.24
    ricular
    0.24
    aque
    0.24
     em
    0.24
    gy
    0.23
    Activations Density 1.125%

    No Known Activations