© 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. 53268
    Prev
    Next
    INDEX
    Explanations

    varied snippets of 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
    zin
    -0.36
    z
    -0.32
     zf
    -0.31
    zb
    -0.30
    zi
    -0.30
    æ¿Ģ
    -0.29
    ZR
    -0.28
    ZF
    -0.28
    za
    -0.28
    sur
    -0.28
    POSITIVE LOGITS
     peas
    0.37
    pez
    0.30
    pe
    0.29
    lene
    0.28
    plen
    0.27
    rlen
    0.26
    pan
    0.26
    ç¡Ŀ
    0.26
    pot
    0.25
    rades
    0.25
    Activations Density 0.007%

    No Known Activations