© 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. 12-TRANSCODER-HP
    7. 23412
    Prev
    Next
    INDEX
    Explanations

    Ske

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    欤
    -0.27
    Class
    -0.25
    éĺ³åħī
    -0.24
    çķĻå®Ī
    -0.24
    Pol
    -0.24
    ynamo
    -0.23
     Wig
    -0.23
    yi
    -0.23
    звезд
    -0.23
    AMI
    -0.23
    POSITIVE LOGITS
    %</
    0.27
     procedures
    0.27
    ultan
    0.27
     fortunes
    0.26
    æĦŁ
    0.25
    ancies
    0.24
    åħĪæĬĬ
    0.24
    åħĭæĸ¯
    0.24
     mass
    0.23
    uc
    0.23
    Activations Density 0.000%

    No Known Activations