© 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. 33-TRANSCODER-HP
    7. 52931
    Prev
    Next
    INDEX
    Explanations

    question marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĴĮåıijå±ķ
    -0.34
    çķĻåľ¨
    -0.28
    éĢģå¾Ģ
    -0.26
    å±Ģ
    -0.26
    åħĴ
    -0.25
     Construct
    -0.25
     па
    -0.24
    è·ijåİ»
    -0.24
    åľĪ
    -0.24
    åĦ¿
    -0.24
    POSITIVE LOGITS
     then
    0.35
     dann
    0.35
    çĦ¶åIJİ
    0.34
    _then
    0.33
    then
    0.31
    Then
    0.30
     Few
    0.29
     WON
    0.28
    oru
    0.28
     Head
    0.28
    Activations Density 0.047%

    No Known Activations