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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 14236
    Prev
    Next
    INDEX
    Explanations

    small

    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
    verture
    -0.08
    online
    -0.07
    	struct
    -0.07
    债券
    -0.07
    atisation
    -0.07
    扬州
    -0.07
     compatibility
    -0.07
    德州
    -0.07
    被列入
    -0.07
    -setup
    -0.07
    POSITIVE LOGITS
     small
    0.12
    小
    0.09
     smaller
    0.09
    small
    0.08
     мал
    0.08
    搪
    0.07
    小组
    0.07
    褂
    0.07
     klein
    0.07
     Small
    0.07
    Activations Density 0.049%

    No Known Activations