© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 38938
    Prev
    Next
    INDEX
    Explanations

    vÃŃt

    np_max-act-logits · gemini-2.0-flash
    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
    im
    -0.31
    root
    -0.30
    etta
    -0.30
    ró
    -0.29
    ragen
    -0.29
    eper
    -0.29
    rh
    -0.28
    rap
    -0.28
    ober
    -0.28
    rÃŃa
    -0.28
    POSITIVE LOGITS
    æľīä¸ĢçĤ¹
    0.27
    å¼±åĬ¿
    0.26
    idi
    0.26
     witnessed
    0.26
     serviced
    0.26
    åı¯çĸij
    0.25
    çĶľç¾İ
    0.25
     decency
    0.25
    IDI
    0.25
    ICY
    0.25
    Activations Density 53.950%

    No Known Activations