© 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. 29286
    Prev
    Next
    INDEX
    Explanations

    medical texts

    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
    严谨
    -0.29
    igy
    -0.28
    çĦ¦èĻij
    -0.27
    hora
    -0.26
    çĶļ
    -0.26
    ocode
    -0.26
    ASSES
    -0.26
    ä½İä¼°
    -0.26
    çķıæĥ§
    -0.25
    @interface
    -0.25
    POSITIVE LOGITS
     Ce
    0.27
    ##_
    0.26
     romantic
    0.26
    æīĵçĶµè¯Ŀ
    0.26
    çĽĪ
    0.26
     he
    0.26
     unavoidable
    0.25
    amel
    0.24
    /WebAPI
    0.23
     generating
    0.23
    Activations Density 1.908%

    No Known Activations