© 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. 22-TRANSCODER-HP
    7. 87008
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uling
    -0.25
    çĸ¢
    -0.25
    roys
    -0.24
    åħ¶éĹ´
    -0.24
    '][]
    -0.23
    ago
    -0.23
     Beg
    -0.23
    permalink
    -0.23
    ego
    -0.23
     è¾
    -0.23
    POSITIVE LOGITS
     clar
    0.27
    çłį
    0.26
    -called
    0.26
    enic
    0.26
    erde
    0.25
    esor
    0.24
     Clar
    0.24
    éļıæŶ
    0.24
     Justi
    0.24
    衽
    0.23
    Activations Density 0.014%

    No Known Activations