© 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. 39866
    Prev
    Next
    INDEX
    Explanations

    Conversational Q&A

    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
    []=
    -0.26
     itemCount
    -0.25
    ioned
    -0.25
    ÂŃing
    -0.24
    ÂŃtion
    -0.24
    æĭĹ
    -0.24
    èĹIJ
    -0.23
     опеÑĢ
    -0.23
    eração
    -0.23
    hower
    -0.23
    POSITIVE LOGITS
    mot
    0.28
     separately
    0.27
    åĪĨåĪ«æĺ¯
    0.26
    è½®
    0.26
     Inst
    0.25
    åĪĨåĪ«ä¸º
    0.25
    å¨Ħ
    0.24
    Inst
    0.24
    ç¥ģ
    0.24
    æ¼ĵ
    0.24
    Activations Density 0.101%

    No Known Activations