© 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. 96045
    Prev
    Next
    INDEX
    Explanations

    random text

    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
    èĤ¾
    -0.44
     neph
    -0.41
    æ³Į
    -0.40
    à¹Ħà¸ķ
    -0.35
     Kid
    -0.33
     kid
    -0.33
    Ren
    -0.33
     Ren
    -0.32
     Nep
    -0.32
     nep
    -0.32
    POSITIVE LOGITS
     crumbs
    0.29
    erval
    0.29
     sill
    0.28
    lemetry
    0.27
    ánh
    0.27
    asury
    0.26
    LOOK
    0.26
    decay
    0.26
    VertexBuffer
    0.26
    åŁ
    0.25
    Activations Density 0.884%

    No Known Activations