© 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. 22344
    Prev
    Next
    INDEX
    Explanations

    favorable/unfavorable

    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
     taraf
    -0.29
    è¾ĥä½İ
    -0.28
    ibs
    -0.27
     hÆ°á»Łng
    -0.26
    ãģĮãĤī
    -0.26
     Torres
    -0.25
    骨头
    -0.25
    çī¢åĽºæłijç«ĭ
    -0.25
    è¾ĥé«ĺ
    -0.24
    ackers
    -0.24
    POSITIVE LOGITS
    缺åı£
    0.27
    EncodingException
    0.26
    -loss
    0.25
    RP
    0.25
    assa
    0.24
     senses
    0.24
    -pres
    0.24
    .yy
    0.24
    _loss
    0.24
    picked
    0.23
    Activations Density 0.015%

    No Known Activations