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. 818
    Prev
    Next
    INDEX
    Explanations

    of

    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
    icit
    -0.29
    .HasValue
    -0.26
    è´¢åĬĽ
    -0.25
     Plum
    -0.25
    çĭ¬è§Ĵåħ½
    -0.25
    Probe
    -0.25
    _msgs
    -0.25
    @m
    -0.24
    national
    -0.24
     OMIT
    -0.24
    POSITIVE LOGITS
    éĩį
    0.27
    ared
    0.26
    aris
    0.26
    ibil
    0.26
    ading
    0.25
     .
    0.25
    缼
    0.25
    æĮ¡
    0.25
    _bulk
    0.25
     Bil
    0.24
    Activations Density 0.007%

    No Known Activations