© 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. 29146
    Prev
    Next
    INDEX
    Explanations

    Incoherent sentences

    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
    apos
    -0.31
    ountry
    -0.27
    iks
    -0.27
    æľ¬äºĭ
    -0.27
    ary
    -0.26
    åİĨæĿ¥
    -0.26
    ette
    -0.25
    ä¸ĸ代
    -0.25
    ãĤģãģ¦
    -0.25
    olas
    -0.24
    POSITIVE LOGITS
     Grande
    0.25
     окÑĢÑĥ
    0.25
    {{$
    0.24
    ä¼ļéĢłæĪIJ
    0.24
    çĵ¶
    0.24
    ropa
    0.24
    ëĭ´
    0.23
    çĵ¶åŃIJ
    0.23
     вÑģÑĤÑĢеÑĩа
    0.23
    æĻ¶
    0.23
    Activations Density 0.191%

    No Known Activations