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. 26198
    Prev
    Next
    INDEX
    Explanations

    assign

    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
     MessageBoxButton
    -0.08
    (Layout
    -0.07
    暴雨
    -0.07
    保驾
    -0.07
     ControllerBase
    -0.07
     европ
    -0.07
    벧
    -0.07
     комплекс
    -0.07
    	global
    -0.07
    秀丽
    -0.07
    POSITIVE LOGITS
     fullest
    0.07
    RD
    0.07
     hairs
    0.07
    "s
    0.06
     Ji
    0.06
    智力
    0.06
    higher
    0.06
    石头
    0.06
    .yellow
    0.06
     HV
    0.06
    Activations Density 0.039%

    No Known Activations