© 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. 14-TRANSCODER-HP
    7. 40190
    Prev
    Next
    INDEX
    Explanations

    climate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ°§
    -0.28
    ç¿»
    -0.26
    ä¸Ģ级
    -0.25
    ç»ĵ
    -0.24
     punches
    -0.24
    èĬ®
    -0.24
    强åĪ¶
    -0.24
     SUS
    -0.24
    æī§
    -0.24
    å¿Ĵ
    -0.24
    POSITIVE LOGITS
    paypal
    0.29
    -null
    0.26
    exter
    0.26
    leased
    0.25
     tink
    0.24
     Coalition
    0.24
    èģĶ
    0.24
    ctor
    0.24
    encies
    0.23
    éĹª
    0.23
    Activations Density 1.837%

    No Known Activations