© 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. 32-TRANSCODER-HP
    7. 42694
    Prev
    Next
    INDEX
    Explanations

    an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icals
    -0.35
    nis
    -0.28
    ni
    -0.27
    ëĭĪ
    -0.25
    nih
    -0.25
    nin
    -0.25
    roud
    -0.24
    è¢ħ
    -0.24
    nant
    -0.24
    nite
    -0.24
    POSITIVE LOGITS
    åIJĪéĩij
    0.28
    åĭ¾
    0.27
    RoutingModule
    0.26
    ereo
    0.26
    ore
    0.26
    anda
    0.25
    å¾ĢæĿ¥
    0.25
    étude
    0.25
    éĩĩ访
    0.25
     a
    0.24
    Activations Density 0.006%

    No Known Activations