© 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. 96648
    Prev
    Next
    INDEX
    Explanations

    Code context

    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
     desi
    -0.25
    bben
    -0.25
     <!--[
    -0.25
     rotary
    -0.25
    cole
    -0.24
     segments
    -0.23
    omic
    -0.23
    çŃīåIJĦç§į
    -0.23
    御
    -0.23
    /dist
    -0.23
    POSITIVE LOGITS
    åĩ»
    0.29
    æī¶
    0.27
    mvc
    0.26
     tá»ij
    0.26
    hint
    0.26
    å°¤
    0.26
    èĵģ
    0.25
    verity
    0.25
     Butt
    0.24
    _INITIALIZER
    0.24
    Activations Density 0.001%

    No Known Activations