© 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. 53848
    Prev
    Next
    INDEX
    Explanations

    -m

    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
    iss
    -0.27
    ibase
    -0.27
    ser
    -0.25
    åĨ¤
    -0.25
    elp
    -0.25
    isan
    -0.25
    -row
    -0.25
    izen
    -0.25
     Large
    -0.24
    æī©
    -0.24
    POSITIVE LOGITS
    EMU
    0.32
    	em
    0.30
     em
    0.29
    acula
    0.27
    emu
    0.27
    (em
    0.26
    acet
    0.26
    _EM
    0.26
    _em
    0.26
    em
    0.26
    Activations Density 0.197%

    No Known Activations