© 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. 40176
    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
    åħ¥åħļ
    -0.28
    xes
    -0.25
    -entry
    -0.25
     Gr
    -0.25
    des
    -0.25
    LETE
    -0.24
    Gr
    -0.24
    çĶļ
    -0.24
    ئ
    -0.24
    eme
    -0.24
    POSITIVE LOGITS
    oland
    0.33
     imag
    0.30
    oogle
    0.30
    åĻªéŁ³
    0.28
    å°ıåºĹ
    0.28
    约è°Ī
    0.27
    ilan
    0.27
    RESOURCE
    0.25
    olan
    0.24
    uffy
    0.24
    Activations Density 0.290%

    No Known Activations

    This feature has no known activations.