Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 1211
    Prev
    Next
    INDEX
    Explanations

    not

    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
     has
    -0.36
     could
    -0.30
     would
    -0.29
    periences
    -0.29
     does
    -0.29
    å°±
    -0.28
     contributes
    -0.28
     continues
    -0.28
     grows
    -0.28
     relates
    -0.27
    POSITIVE LOGITS
    loth
    0.31
    Hostname
    0.26
     Beginners
    0.25
    åīįåĪĹ
    0.25
     everybody
    0.25
     Horton
    0.25
    dsn
    0.25
    åıijå¸ĥæĹ¶éĹ´
    0.25
    pac
    0.25
     Being
    0.24
    Activations Density 0.010%

    No Known Activations