© 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. 54348
    Prev
    Next
    INDEX
    Explanations

    infection

    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
    od
    -0.28
    éŁ³é¢ij
    -0.28
    KG
    -0.26
    mut
    -0.26
    dsp
    -0.26
    pong
    -0.25
    èģĮåľº
    -0.25
     Pav
    -0.25
    èµ°
    -0.25
    çĥĪ
    -0.24
    POSITIVE LOGITS
     infections
    0.30
    eft
    0.28
     infection
    0.26
    æĦŁæŁĵ
    0.26
    acter
    0.26
    iaux
    0.26
     inoc
    0.26
    rote
    0.25
     infect
    0.25
     viruses
    0.25
    Activations Density 0.016%

    No Known Activations