© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112011
    Prev
    Next
    INDEX
    Explanations

    Technical definitions/code

    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
     Abbott
    -0.27
    å°ıå¿ĥ
    -0.26
    åıĹ欢è¿İ
    -0.26
    éo
    -0.25
    çĶŁäº§è½¦éĹ´
    -0.25
    ÑĢид
    -0.25
    achts
    -0.24
    æľī害
    -0.24
    æĿ²
    -0.24
    uck
    -0.24
    POSITIVE LOGITS
    isme
    0.30
    “
    0.28
     palms
    0.27
    yah
    0.25
    entially
    0.25
    ãĢĮ
    0.25
    éĴ´
    0.25
    ë§Īëĭ¤
    0.24
    ×ķש
    0.23
     Corinthians
    0.23
    Activations Density 0.005%

    No Known Activations