© 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. 95892
    Prev
    Next
    INDEX
    Explanations

    send

    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
    æ±ģ
    -0.33
    iverse
    -0.29
    äºĨæĪijçļĦ
    -0.27
    èģĶç³»
    -0.27
    ä¼łè¾¾
    -0.27
    åĴ©
    -0.27
    Contacts
    -0.26
    ().__
    -0.26
    带åĽŀ
    -0.26
    Cx
    -0.25
    POSITIVE LOGITS
    auen
    0.29
     positive
    0.28
     doInBackground
    0.28
     more
    0.28
     negative
    0.27
    onium
    0.27
    æĽ´å¤ļ
    0.25
    ancell
    0.25
    éĺ³æĢ§
    0.25
    enz
    0.24
    Activations Density 0.002%

    No Known Activations