© 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. 43181
    Prev
    Next
    INDEX
    Explanations

    Computer science

    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
    åĬĽ
    -1.36
     force
    -1.30
    force
    -1.23
     forces
    -1.22
     Force
    -1.20
    Force
    -1.18
    -force
    -1.13
    åĬĽéĩı
    -1.08
     Forces
    -1.07
     FORCE
    -1.07
    POSITIVE LOGITS
    ois
    0.28
    ipop
    0.26
    àºį
    0.25
    STALL
    0.24
    oms
    0.24
    è³ĵ
    0.23
    OrNull
    0.23
    undry
    0.23
    æķĹ
    0.23
    æķijåij½
    0.23
    Activations Density 0.003%

    No Known Activations