© 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. 95625
    Prev
    Next
    INDEX
    Explanations

    Code and text snippets

    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
    empor
    -0.27
    æİĴè¡Įæ¦ľ
    -0.26
     ÐĴедÑĮ
    -0.26
    çĶ²
    -0.26
    çĻ¸
    -0.25
    à¹ģà¸ŀ
    -0.24
    åĩĢåĢ¼
    -0.23
     Reflect
    -0.23
    _Tick
    -0.23
     Ethan
    -0.23
    POSITIVE LOGITS
    lage
    0.26
    oms
    0.26
    Ng
    0.24
    çįł
    0.24
     spr
    0.24
    laus
    0.24
    aign
    0.24
    ugal
    0.24
    angelo
    0.24
    activate
    0.23
    Activations Density 0.102%

    No Known Activations