© 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. 23705
    Prev
    Next
    INDEX
    Explanations

    evolution

    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
     stump
    -0.28
    brief
    -0.28
    łģ
    -0.27
    hlen
    -0.26
    æĦıè§ģåıįé¦Ī
    -0.26
    iners
    -0.26
    extends
    -0.26
    åĸĨ
    -0.26
    inus
    -0.26
    arius
    -0.26
    POSITIVE LOGITS
    миÑĢ
    0.26
     Predicate
    0.26
    çĶĦ
    0.25
    èĩªçIJĨ
    0.25
     Entr
    0.25
    åIJĮå¿ĥ
    0.25
    åĩłåı¥
    0.24
    çı¥
    0.24
     Beg
    0.24
    ÑĤик
    0.24
    Activations Density 0.025%

    No Known Activations