© 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. 25-TRANSCODER-HP
    7. 109152
    Prev
    Next
    INDEX
    Explanations

    obtaining

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    累积
    -0.31
    TED
    -0.26
    è¯Ń
    -0.26
    éĢļçŁ¥ä¹¦
    -0.26
    iggs
    -0.25
     accumulate
    -0.25
    å¤ķ
    -0.24
    轨
    -0.24
     accumulating
    -0.24
    æĸ½å·¥åįķä½į
    -0.24
    POSITIVE LOGITS
    CHA
    0.27
    ä¹į
    0.27
    cha
    0.26
    åľĺ
    0.26
    åѦéĹ®
    0.25
    ABL
    0.25
    chas
    0.25
    æŁ´
    0.24
    KER
    0.24
    ãĤĴéĢļ
    0.24
    Activations Density 0.923%

    No Known Activations