© 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. 39564
    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
    trägt
    -0.28
    soever
    -0.28
    éĹŃ
    -0.27
    bourne
    -0.27
    LOY
    -0.27
    @stop
    -0.26
    å¿«æĬ¥
    -0.26
     setContentView
    -0.25
    éĥ½å¸ĤæĬ¥
    -0.25
    åĢĴéľī
    -0.25
    POSITIVE LOGITS
    0
    0.39
    inc
    0.38
    in
    0.37
    part
    0.35
    ap
    0.34
    e
    0.33
    day
    0.33
    2
    0.33
    1
    0.33
    4
    0.32
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.