© 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
    2. Qwen3-4B
    3. 32-TRANSCODER-HP
    4. 42357
    Prev
    Next
    INDEX
    Explanations

    Code and databases

    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
    oti
    -0.30
    æķ£
    -0.29
    caa
    -0.28
    å¡ŀ
    -0.25
    æ²¹èħ»
    -0.25
    (bucket
    -0.25
     Ca
    -0.24
    åį¯
    -0.24
    ryo
    -0.24
    (shape
    -0.24
    POSITIVE LOGITS
    TURE
    0.28
    ware
    0.26
    amble
    0.26
     rew
    0.25
    WB
    0.25
    èį
    0.25
    åħ¨èĥ½
    0.25
     hub
    0.25
    ward
    0.24
    ãĥĻãĥ³
    0.24
    Activations Density 0.000%

    No Known Activations