© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161879
    Prev
    Next
    INDEX
    Explanations

    Spatial relationships/placement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    解éĩĬ
    -0.31
    表çİ°
    -0.25
    éĢĤåºĶ
    -0.24
     legalized
    -0.24
    ç§ĭ
    -0.24
    解éĩĭ
    -0.24
    -pic
    -0.24
     pred
    -0.24
    碧
    -0.24
    çŃĸåĪĴ
    -0.24
    POSITIVE LOGITS
    gap
    0.29
     gap
    0.28
     sidel
    0.27
    ä¸įçķĻ
    0.27
     gaps
    0.26
    gain
    0.26
    åĺ´
    0.26
    |`↵
    0.25
    hea
    0.25
    gado
    0.24
    Activations Density 0.005%

    No Known Activations