© 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. 25-TRANSCODER-HP
    7. 107962
    Prev
    Next
    INDEX
    Explanations

    financial matters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éļIJ
    -0.30
    åIJ¬
    -0.30
    tent
    -0.29
    å¥Ĺ
    -0.27
    sters
    -0.27
    åIJ¬çĿĢ
    -0.27
     Stout
    -0.26
    upo
    -0.26
    çݰ象
    -0.26
     Charg
    -0.26
    POSITIVE LOGITS
    ç®´
    0.30
    EXPORT
    0.26
     pipe
    0.26
    ikel
    0.25
    å¾Ģä¸ĭ
    0.25
     forward
    0.25
     decentralized
    0.25
    ain
    0.25
    acic
    0.24
     spending
    0.24
    Activations Density 0.914%

    No Known Activations