© 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. 53734
    Prev
    Next
    INDEX
    Explanations

    Language and code

    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
    ä½ľåĵģåĨħ容
    -0.29
     Sellers
    -0.28
     sellers
    -0.28
    åįĸ家
    -0.28
    adora
    -0.26
     asc
    -0.26
    çĶŁæ´»åľ¨
    -0.26
    peria
    -0.25
    oe
    -0.25
    éĢģè¾¾
    -0.25
    POSITIVE LOGITS
     power
    0.29
    Power
    0.28
    -building
    0.27
    ouched
    0.27
    č
    0.26
     powers
    0.26
     ability
    0.26
     building
    0.26
    powered
    0.25
    åIJĦ级
    0.25
    Activations Density 0.009%

    No Known Activations