© 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. 33-TRANSCODER-HP
    7. 53960
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hete
    -0.31
    forc
    -0.28
     mol
    -0.26
    brace
    -0.26
     bev
    -0.26
    orama
    -0.25
    åĪĹ
    -0.25
     gi
    -0.25
    è¶ħåĩº
    -0.25
     préc
    -0.24
    POSITIVE LOGITS
    ch
    0.32
     ch
    0.29
    Ch
    0.28
    çļĦ人çĶŁ
    0.27
    ç§ĭ
    0.26
    辫
    0.26
    CH
    0.26
     Ch
    0.26
    chas
    0.26
    åĩłå®¶
    0.25
    Activations Density 0.030%

    No Known Activations