© 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. 27-TRANSCODER-HP
    7. 57155
    Prev
    Next
    INDEX
    Explanations

    cancer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹ¾
    -0.28
    emble
    -0.26
     Pulse
    -0.26
    æļĹæļĹ
    -0.26
    docs
    -0.26
    uli
    -0.25
    forc
    -0.25
     publish
    -0.24
    iked
    -0.24
    pline
    -0.24
    POSITIVE LOGITS
    ç±½
    0.27
     stain
    0.27
    第ä¸Ģæī¹
    0.26
    æĹıèĩªæ²»åİ¿
    0.26
    æĦŁæŁĵ
    0.26
    éģĹä¼ł
    0.26
    ç§ijåѦ
    0.26
    çĶŁçī©
    0.25
     bead
    0.25
    å¯Įè´µ
    0.25
    Activations Density 0.004%

    No Known Activations