© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161828
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    вел
    -0.30
     froze
    -0.26
    Didn
    -0.26
    иде
    -0.25
    åıĤåĬłäºĨ
    -0.25
    rove
    -0.25
    åįłæį®äºĨ
    -0.25
    PLIER
    -0.25
    äºĨä¸Ģåľº
    -0.25
     Isle
    -0.24
    POSITIVE LOGITS
    pc
    0.31
    pic
    0.26
    ught
    0.25
    ase
    0.25
    pires
    0.24
    ta
    0.24
     pam
    0.24
    ãģıãģł
    0.24
    è§Ħå®ļçļĦ
    0.24
    licant
    0.24
    Activations Density 0.004%

    No Known Activations