© 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. 18-TRANSCODER-HP
    7. 88509
    Prev
    Next
    INDEX
    Explanations

    punctuation/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vell
    -0.27
    æѤå¤Ħ
    -0.27
    @JsonProperty
    -0.27
    èģ
    -0.26
    -man
    -0.25
    ä¸įçŁ¥
    -0.24
    ivating
    -0.24
    _MAXIMUM
    -0.24
    ,No
    -0.24
    âĢ¦I
    -0.24
    POSITIVE LOGITS
    aller
    0.29
    åĬłå¿«åıijå±ķ
    0.28
    åįıåIJĮåıijå±ķ
    0.27
    alis
    0.27
     decor
    0.26
    ounds
    0.26
    defer
    0.25
     drunken
    0.25
    å±ķ示äºĨ
    0.25
    uger
    0.25
    Activations Density 66.973%

    No Known Activations