© 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. 129890
    Prev
    Next
    INDEX
    Explanations

    common words

    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
    ablish
    -0.30
    éĹªåħī
    -0.29
    evity
    -0.29
    º«
    -0.28
    lessness
    -0.27
    çĦī
    -0.26
    ä¸ĩæĪ·
    -0.26
    erea
    -0.26
    lage
    -0.26
    NSE
    -0.25
    POSITIVE LOGITS
    è¾ĥå¿«
    0.27
    gie
    0.25
    _checked
    0.24
     Faster
    0.24
    æݳ
    0.24
    åĺ¤
    0.24
    obb
    0.24
    Cent
    0.23
    culo
    0.23
     diá»ħn
    0.23
    Activations Density 0.002%

    No Known Activations