© 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. 31-TRANSCODER-HP
    7. 19080
    Prev
    Next
    INDEX
    Explanations

    Online discussion context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dez
    -0.28
    Kal
    -0.27
    åĪ»
    -0.26
     accidental
    -0.26
    signature
    -0.26
    Sig
    -0.26
    asks
    -0.25
    ä¸Ģä¸ĩ
    -0.25
    åľ°
    -0.25
     asks
    -0.25
    POSITIVE LOGITS
     days
    0.31
    è½»
    0.26
    è¿Ľ
    0.26
     wo
    0.26
    mic
    0.25
     locks
    0.25
    nah
    0.25
     Civil
    0.25
     turns
    0.24
    mile
    0.24
    Activations Density 0.003%

    No Known Activations