© 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. 57162
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    hu
    -0.28
    startup
    -0.27
    standing
    -0.27
    cp
    -0.27
    start
    -0.26
     insanların
    -0.26
    (cp
    -0.25
    èľķ
    -0.25
    .Startup
    -0.25
    éļ¼
    -0.25
    POSITIVE LOGITS
    wich
    0.28
    ,false
    0.26
    åĵģ
    0.26
    âĬĶ
    0.25
    åİĤåĮº
    0.25
    æīŃ
    0.25
    çģŃ亡
    0.25
    ä»
    0.24
     createContext
    0.24
    éļĪ
    0.24
    Activations Density 0.002%

    No Known Activations