© 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. 27-TRANSCODER-HP
    7. 58069
    Prev
    Next
    INDEX
    Explanations

    direct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rench
    -0.28
    @d
    -0.27
     beside
    -0.26
    urope
    -0.26
     Incorporated
    -0.25
     glued
    -0.25
    irl
    -0.24
    代价
    -0.24
     Wrapped
    -0.24
    idis
    -0.24
    POSITIVE LOGITS
     direct
    0.33
    lier
    0.32
     determination
    0.27
     hab
    0.27
    headed
    0.27
    -done
    0.27
    direct
    0.26
    侨
    0.26
     mutual
    0.26
     immediate
    0.26
    Activations Density 0.016%

    No Known Activations