© 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. 32-TRANSCODER-HP
    7. 41958
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -0.50
    then
    -0.47
    åĪĻ
    -0.43
     THEN
    -0.41
     Then
    -0.40
     entonces
    -0.39
    Then
    -0.38
    åĪĻæĺ¯
    -0.35
    ï¼ĮåĪĻ
    -0.35
    åīĩ
    -0.35
    POSITIVE LOGITS
     autres
    0.30
    åħ¶ä»ĸ
    0.28
    drv
    0.26
    uesto
    0.26
    /javascript
    0.26
     other
    0.26
    ormsg
    0.25
     functional
    0.25
    éĢıè§Ĩ
    0.24
    åħ¶ä»ĸçļĦ
    0.24
    Activations Density 0.001%

    No Known Activations