© 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. 9-TRANSCODER-HP
    7. 29255
    Prev
    Next
    INDEX
    Explanations

    incident/incoming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    液
    -0.28
    liness
    -0.27
    little
    -0.26
    串
    -0.26
    çIJĥ
    -0.26
    èĢ½
    -0.25
    æĮģä¹ħ
    -0.25
    éĥ¨åĪĨåĨħ容
    -0.25
    åĢį
    -0.25
    容
    -0.25
    POSITIVE LOGITS
    ijo
    0.28
    èĮ¬
    0.27
    argo
    0.26
    ivo
    0.26
    ihad
    0.26
    atedRoute
    0.26
    styleType
    0.25
     succesfully
    0.25
     purposely
    0.24
    æĭIJ
    0.24
    Activations Density 0.336%

    No Known Activations