© 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. 95966
    Prev
    Next
    INDEX
    Explanations

    national or state

    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
    èŀºæĹĭ
    -0.27
     Stern
    -0.27
     fre
    -0.27
    äºķ
    -0.26
    *>
    -0.26
    软
    -0.26
    åĭ¤
    -0.26
    æī¶
    -0.26
    mw
    -0.26
    ÙĩÙĪ
    -0.25
    POSITIVE LOGITS
     natural
    0.34
    natural
    0.32
    èĩªçĦ¶
    0.32
     tinder
    0.31
     lands
    0.30
    天çĦ¶
    0.30
    Natural
    0.29
     Natural
    0.28
    pga
    0.28
    湿
    0.27
    Activations Density 0.104%

    No Known Activations