© 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. 27-TRANSCODER-HP
    7. 8376
    Prev
    Next
    INDEX
    Explanations

    efficiency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getContent
    -0.27
    uli
    -0.27
    é«ĺå±Ĥ
    -0.27
    æ·±åİļçļĦ
    -0.27
    æĽ´æ·±
    -0.27
    åģ¥åº·
    -0.26
     Overnight
    -0.26
    ukkan
    -0.26
     profound
    -0.26
    çģ«å±±
    -0.25
    POSITIVE LOGITS
    æķĪçİĩ
    0.38
     efficiency
    0.34
     efficiencies
    0.32
     Efficiency
    0.29
    横åIJij
    0.27
    -ie
    0.26
    eid
    0.26
    å·¥ä½ľæķĪçİĩ
    0.25
    lient
    0.25
     prep
    0.24
    Activations Density 0.002%

    No Known Activations