© 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. 31-TRANSCODER-HP
    7. 19044
    Prev
    Next
    INDEX
    Explanations

    Amazon products

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĶ
    -0.25
    enton
    -0.25
    _kses
    -0.24
    骸
    -0.24
    sse
    -0.24
    é«ĺ空
    -0.23
    天空
    -0.23
    ä¹±
    -0.23
    踯
    -0.23
     abide
    -0.23
    POSITIVE LOGITS
    çģ«çĥ§
    0.31
    çģ«
    0.30
    adero
    0.30
     Fi
    0.28
    folios
    0.28
    _FF
    0.28
     anonymously
    0.26
    è¿¢
    0.26
    care
    0.26
     бил
    0.26
    Activations Density 0.018%

    No Known Activations