© 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. 95355
    Prev
    Next
    INDEX
    Explanations

    already been

    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
    freq
    -0.27
    ãģ¾ãģģ
    -0.26
    PATCH
    -0.25
    olv
    -0.24
    leh
    -0.23
     core
    -0.23
    è¯į
    -0.23
    OutputStream
    -0.23
    @show
    -0.23
    åĪĹ为
    -0.23
    POSITIVE LOGITS
    已被
    0.53
    å·²ç»ı被
    0.46
    been
    0.43
    ’ve
    0.42
    å·²
    0.41
    've
    0.40
     been
    0.39
     Äijã
    0.38
     telah
    0.36
    has
    0.36
    Activations Density 0.902%

    No Known Activations