© 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. 53462
    Prev
    Next
    INDEX
    Explanations

    Code and long passages

    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
    mers
    -0.31
    mer
    -0.30
    tep
    -0.28
     diam
    -0.26
     colder
    -0.26
    é²Ķ
    -0.26
    åĴ¬
    -0.26
    stp
    -0.26
    incer
    -0.26
    master
    -0.26
    POSITIVE LOGITS
    urm
    0.29
     Barb
    0.27
    rient
    0.26
    UR
    0.26
     Haram
    0.25
    身边
    0.25
     Sext
    0.24
    èIJ
    0.24
    оÑĢм
    0.24
     Her
    0.24
    Activations Density 0.006%

    No Known Activations