© 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. 99275
    Prev
    Next
    INDEX
    Explanations

    comfort

    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
    è¾Ľèĭ¦
    -0.26
    hesion
    -0.25
    äºĭæķħåıijçĶŁ
    -0.25
    mand
    -0.25
    åĦ¿
    -0.24
    rnd
    -0.24
    mi
    -0.24
    ɵ
    -0.24
     cfg
    -0.23
    uristic
    -0.23
    POSITIVE LOGITS
     with
    0.30
     NL
    0.28
     DF
    0.27
     DE
    0.26
    è²Ĥ
    0.26
    JE
    0.25
     DEA
    0.25
    尤为
    0.25
     II
    0.25
     especially
    0.24
    Activations Density 0.016%

    No Known Activations