© 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. 32-TRANSCODER-HP
    7. 41384
    Prev
    Next
    INDEX
    Explanations

    census population

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _survey
    -0.30
    survey
    -0.30
    earing
    -0.27
    æĬĢæľ¯æĶ¯æĮģ
    -0.27
    Survey
    -0.27
     weight
    -0.25
    rts
    -0.25
    Servers
    -0.24
    getStore
    -0.24
     betray
    -0.24
    POSITIVE LOGITS
     Coff
    0.30
    å§Ķ
    0.28
    elib
    0.28
    ancia
    0.28
     PL
    0.27
     ap
    0.27
    -c
    0.27
    .FR
    0.26
    PC
    0.25
    커
    0.25
    Activations Density 0.018%

    No Known Activations