© 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. 95842
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
    aste
    -0.31
    -sub
    -0.26
     ÑĤо
    -0.26
    åĨĮ
    -0.25
    空
    -0.25
     terms
    -0.25
     ÙĪÙĦÙħ
    -0.25
    /cache
    -0.24
     last
    -0.24
    -term
    -0.24
    POSITIVE LOGITS
     underneath
    0.27
    åıĹä¸įäºĨ
    0.27
    ighbor
    0.27
     Owned
    0.26
     away
    0.26
    egal
    0.26
    Away
    0.25
    æ¸ĹéĢı
    0.25
     apart
    0.25
    ographically
    0.25
    Activations Density 0.012%

    No Known Activations