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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 6813
    Prev
    Next
    INDEX
    Explanations

    Bee pollination of food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'post
    -0.06
    asyarakat
    -0.06
    现行
    -0.06
    方案
    -0.06
    𩾃
    -0.06
    Ƞ
    -0.06
    몴
    -0.06
    �
    -0.06
     Democr
    -0.06
     להעביר
    -0.06
    POSITIVE LOGITS
    clip
    0.09
    开心
    0.07
    מוג
    0.07
    ycles
    0.07
     Active
    0.07
    cline
    0.07
     explains
    0.07
     caveat
    0.07
     ه
    0.07
     ceremon
    0.07
    Activations Density 0.009%

    No Known Activations