© 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. 88649
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    以åıĬ
    -0.35
    以åıĬåħ¶ä»ĸ
    -0.33
    使æĪij
    -0.29
    viously
    -0.27
    ãģĬãĤĪãģ³
    -0.27
    ELCOME
    -0.26
    æīĢ以æĪij
    -0.26
    uder
    -0.26
    URNS
    -0.26
    Sorry
    -0.25
    POSITIVE LOGITS
    æīįè¡Į
    0.33
     Rep
    0.27
    äºĨä¸Ģä¸ĭ
    0.25
    persist
    0.24
    gon
    0.24
    's
    0.23
    ts
    0.23
    ëĵ¯
    0.23
    ä¹ħäºĨ
    0.23
     accordingly
    0.23
    Activations Density 0.008%

    No Known Activations