© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39582
    Prev
    Next
    INDEX
    Explanations

    financial/business context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çģµæ´»
    -0.28
    åı¯è¡Į
    -0.27
    еÑĢи
    -0.27
    åıį驳
    -0.26
    è±ģ
    -0.26
    itive
    -0.24
    彦
    -0.24
    ä¸ĵç§ij
    -0.24
    常è§Ħ
    -0.24
    çĭŃ
    -0.24
    POSITIVE LOGITS
     charged
    0.30
     charge
    0.26
    eltas
    0.26
    æľ¬é¢Ĩ
    0.25
     prosecutions
    0.25
     ejected
    0.25
     Signed
    0.25
     fulfilled
    0.25
    맥
    0.24
    elta
    0.24
    Activations Density 0.144%

    No Known Activations