© 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. 35-TRANSCODER-HP
    7. 39635
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |
    -0.28
    çļĦè·Ŀ离
    -0.27
    gro
    -0.26
    -pres
    -0.25
    çİ°
    -0.25
    绣ä¸Ģ
    -0.24
    èµĦ
    -0.23
    è¿Ļ份
    -0.23
    çļĦæķĪæŀľ
    -0.23
    è¿ĺåİŁ
    -0.23
    POSITIVE LOGITS
    enery
    0.27
    osas
    0.25
    rapid
    0.25
    _prec
    0.25
    á»ħn
    0.25
     Trap
    0.24
    ạch
    0.24
    ãĤŃãĥ£ãĥ³
    0.24
    avis
    0.24
    enes
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.