© 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. 95887
    Prev
    Next
    INDEX
    Explanations

    question and answer

    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
    ượt
    -0.27
     lick
    -0.26
    çķĻç»Ļ
    -0.26
    soon
    -0.26
    rowse
    -0.25
    unders
    -0.25
    inline
    -0.24
    roman
    -0.24
    ç«ŀéĢī
    -0.24
    resse
    -0.24
    POSITIVE LOGITS
    sweet
    0.27
     arm
    0.27
     intermediate
    0.27
     Intermediate
    0.26
     diff
    0.26
     groups
    0.25
     sweet
    0.25
    è´§æºIJ
    0.25
    aco
    0.25
    feed
    0.25
    Activations Density 0.884%

    No Known Activations