© 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. 22-TRANSCODER-HP
    7. 112455
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chemes
    -0.28
    nown
    -0.26
     algo
    -0.25
    缣
    -0.24
    æĸ°è§Ħ
    -0.24
    matter
    -0.24
    TOT
    -0.24
     schemes
    -0.24
     soll
    -0.23
    measurement
    -0.23
    POSITIVE LOGITS
    æī¿æĭħ责任
    0.26
    æĪIJ为ä¸Ģ个
    0.26
    åĪ°è¿ĻéĩĮ
    0.26
    å¤ĩçĶ¨
    0.25
     note
    0.25
    为ä¸Ģä½ĵ
    0.25
    ilogue
    0.25
     Final
    0.25
     же
    0.25
    èĩªçĦ¶ä¿ĿæĬ¤
    0.24
    Activations Density 0.017%

    No Known Activations