© 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. 87938
    Prev
    Next
    INDEX
    Explanations

    science and technology

    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
    è¾ķ
    -0.27
    æīįæĺ¯çľŁæŃ£
    -0.26
    ãģĤãĤĭ
    -0.25
    çĪ¹
    -0.25
     scare
    -0.24
     GRID
    -0.24
    æĢ»å±Ģ
    -0.23
    ä¹Łåıªèĥ½
    -0.23
    å½ĵåľ°äºº
    -0.23
    ãģ®ä¸Ģ
    -0.23
    POSITIVE LOGITS
    sworth
    0.28
    çĶŁçĶŁ
    0.27
    åļ¼
    0.27
     leaf
    0.26
    æijĺ
    0.26
     Leaf
    0.25
    缩
    0.25
    rew
    0.25
     intr
    0.25
     seaw
    0.25
    Activations Density 0.006%

    No Known Activations