© 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. 43489
    Prev
    Next
    INDEX
    Explanations

    code and citations

    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
    èĩªåĬ¨
    -0.28
     automatic
    -0.27
     Automatic
    -0.26
    æŁĵ
    -0.26
    è¿IJåĬ¨
    -0.25
    spath
    -0.25
    Automatic
    -0.25
    Naz
    -0.25
    Auto
    -0.24
    ìŀIJëıĻ
    -0.24
    POSITIVE LOGITS
     Pe
    0.30
    prm
    0.29
    oki
    0.29
    LETE
    0.28
     peer
    0.28
     pe
    0.28
    PK
    0.28
    _p
    0.28
    PR
    0.28
    _pr
    0.28
    Activations Density 0.004%

    No Known Activations