© 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. 30-TRANSCODER-HP
    7. 95924
    Prev
    Next
    INDEX
    Explanations

    moral

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sack
    -0.28
    éĢīæīĭ
    -0.27
    åıĭè°Ĭ
    -0.26
     sling
    -0.26
    è¯ķ
    -0.25
     pity
    -0.25
     Filename
    -0.24
    IW
    -0.24
    è°ħ解
    -0.24
    ën
    -0.24
    POSITIVE LOGITS
     system
    0.30
    system
    0.29
    è§Ħå®ļçļĦ
    0.28
    ä¼ł
    0.28
    ç³»ç»Ł
    0.27
    á¹ĥ
    0.27
     resourceId
    0.26
    sist
    0.26
    specs
    0.26
    olta
    0.26
    Activations Density 0.014%

    No Known Activations