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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 27417
    Prev
    Next
    INDEX
    Explanations

    DR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    完毕
    -0.07
    SelectedItem
    -0.07
    _DIFF
    -0.07
    푼
    -0.06
    _tip
    -0.06
    你就
    -0.06
    悆
    -0.06
     Item
    -0.06
    箔
    -0.06
    .Username
    -0.06
    POSITIVE LOGITS
    𝙖
    0.07
    ♑
    0.07
     realpath
    0.07
     hút
    0.07
    🤦
    0.07
     הדרך
    0.07
     recruiters
    0.07
    lake
    0.07
     máquina
    0.07
     الجامعة
    0.07
    Activations Density 0.017%

    No Known Activations